© 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. 22-GEMMASCOPE-RES-131K
    7. 12485
    Prev
    Next
    INDEX
    Explanations

    variable assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.50
     to
    -1.26
     then
    -1.16
    <eos>
    -0.98
     also
    -0.97
    -
    -0.97
    prec
    -0.93
    *
    -0.93
     “
    -0.91
    [
    -0.91
    POSITIVE LOGITS
    எ
    1.10
    مقال
    1.02
    utando
    1.02
    dicionado
    1.00
    räck
    1.00
    面積
    0.99
    Bibliografie
    0.98
     distanciation
    0.97
    ophanes
    0.96
    reonine
    0.96
    Activations Density 0.004%

    No Known Activations