© 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. 244877
    Prev
    Next
    INDEX
    Explanations

    actions, features, and materials

    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
    逺
    0.57
    𝒗
    0.57
    uito
    0.55
     aproveitar
    0.54
    сты
    0.54
    Otros
    0.53
    סט
    0.52
    דו
    0.52
    ｏ
    0.52
    𝒉
    0.51
    POSITIVE LOGITS
     TBA
    0.52
     Pro
    0.49
     TMZ
    0.49
     Williams
    0.48
     Media
    0.46
     Education
    0.46
     Paramount
    0.46
     pretrial
    0.45
     Rowing
    0.45
     markedly
    0.45
    Activations Density 0.001%

    No Known Activations