© 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. 206319
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    Communication or seeking information

    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
     הק
    0.53
    키
    0.51
    जे
    0.49
    ки
    0.49
    හ
    0.48
    미
    0.48
    ה
    0.47
    ३
    0.47
     کي
    0.46
    mith
    0.46
    POSITIVE LOGITS
     Always
    0.57
     Instead
    0.45
     Phyt
    0.44
     These
    0.44
     Valuable
    0.43
     Therefore
    0.42
     Snowdon
    0.42
     Driver
    0.41
    Always
    0.41
     Assad
    0.41
    Activations Density 0.001%

    No Known Activations