© 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. 73420
    Prev
    Next
    INDEX
    Explanations

    polynomials and expressions

    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
     všetkých
    -1.02
     Новости
    -0.91
    リエ
    -0.91
     cetera
    -0.89
    ficial
    -0.88
    ELE
    -0.87
    nment
    -0.87
    ватися
    -0.87
    άν
    -0.86
    控制
    -0.86
    POSITIVE LOGITS
    かで
    0.90
     standby
    0.87
     remain
    0.86
    фии
    0.85
     наконец
    0.85
     мали
    0.82
     Lastly
    0.79
     econô
    0.79
    ratic
    0.78
     graduating
    0.78
    Activations Density 0.018%

    No Known Activations