© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239149
    Prev
    Next
    INDEX
    Explanations

    lists of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     आइड
    0.54
     allgemeinen
    0.51
    󠁢
    0.51
    ಪಿ
    0.49
     بسي
    0.49
     Konzept
    0.49
     ehemaligen
    0.49
    र्गत
    0.49
    നില്‍
    0.49
    ږئ
    0.49
    POSITIVE LOGITS
    却
    0.46
    “
    0.45
    /
    0.44
     product
    0.43
     Laplacian
    0.42
    密度
    0.41
     qubits
    0.41
     (“
    0.41
     developers
    0.39
    一把
    0.39
    Activations Density 0.000%

    No Known Activations