© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33354
    Prev
    Next
    INDEX
    Explanations

    variable names and declarations

    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
     condicionado
    -1.65
     škoda
    -1.65
    Every
    -1.59
    ＊＊＊＊
    -1.56
    Both
    -1.55
    During
    -1.54
    Taking
    -1.52
    Jeśli
    -1.52
    昨日は
    -1.52
    Wszyst
    -1.51
    POSITIVE LOGITS
    などが
    1.66
    j
    1.46
    などを
    1.43
    _
    1.41
    po
    1.41
    を
    1.41
    e
    1.40
    w
    1.39
    er
    1.38
    g
    1.37
    Activations Density 0.011%

    No Known Activations