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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104133
    Prev
    Next
    INDEX
    Explanations

    names followed by punctuation or assignments

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

    closing brackets or quote marks in code, particularly after array keys or variable names.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     and
    -2.08
    However
    -1.77
     the
    -1.52
    which
    -1.51
    Though
    -1.46
    om
    -1.45
     ؛
    -1.45
    b
    -1.43
     Harian
    -1.41
    -&
    -1.34
    POSITIVE LOGITS
     same
    1.88
     ältere
    1.64
     äldre
    1.62
     last
    1.58
    zeu
    1.55
     justamente
    1.55
     autre
    1.52
    FormUrlEncoded
    1.51
     jego
    1.49
    RAHAM
    1.48
    Activations Density 0.019%

    No Known Activations