© 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. 12789
    Prev
    Next
    INDEX
    Explanations

    nut connected, chewy texture, loop amongst

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

    The neuron fires on uncommon, domain-specific technical or product terms (e.g. specialized equipment names, jargon, or proper nouns) rather than everyday words.

    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
     from
    -1.77
    Our
    -1.77
     tampaknya
    -1.59
    Instead
    -1.52
    imbang
    -1.50
    ﾓ
    -1.48
    ？』
    -1.45
    owohl
    -1.44
     including
    -1.43
    閔
    -1.42
    POSITIVE LOGITS
    f
    2.13
    la
    1.88
    d
    1.78
    c
    1.75
    ts
    1.72
    m
    1.66
     LIABLE
    1.65
    "},
    1.61
    am
    1.61
    p
    1.60
    Activations Density 0.114%

    No Known Activations