© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9503
    Prev
    Next
    INDEX
    Explanations

    Dietrich Spear / momentary anger / pyrrolidine viability

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical or programming terms related to specific libraries, compounds, or programming functions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on rare, domain-specific proper nouns and technical identifiers—e.g. library names, protein or chemical names, function names, author surnames, model names, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    渽
    -3.22
    酲
    -2.91
    勦
    -2.56
    va
    -2.50
    艽
    -2.44
    й
    -2.41
    ⬯
    -2.39
    i
    -2.39
    "=>$
    -2.38
    geſ
    -2.36
    POSITIVE LOGITS
    骉
    2.88
    逦
    2.70
    所说的
    2.55
    鸱
    2.53
     améli
    2.41
     tranſ
    2.41
     meilleur
    2.39
     rumbling
    2.38
     étab
    2.33
    ні
    2.28
    Activations Density 0.006%

    No Known Activations