© 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. 10953
    Prev
    Next
    INDEX
    Explanations

    company plc or academic grades

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

    The neuron fires on short uppercase or mixed‐case abbreviations and legal/technical acronyms (e.g. “plc,” “SNR,” “imread”).

    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
    d
    -3.20
    v
    -2.70
    m
    -2.70
    u
    -2.48
     fiercely
    -2.36
    
    -2.33
     be
    -2.33
    x
    -2.22
     relentlessly
    -2.20
     brauche
    -2.17
    POSITIVE LOGITS
    猡
    2.52
    </i>
    2.48
    
    2.25
    鉿
    2.23
    锨
    2.14
     \_
    2.14
    та
    2.14
    ⬯
    2.13
     декабря
    2.11
    utate
    2.11
    Activations Density 0.002%

    No Known Activations