© 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. 234894
    Prev
    Next
    INDEX
    Explanations

    runway director

    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
    agę
    0.63
     جوړونکو
    0.56
    بيب
    0.54
    óz
    0.54
    胰
    0.54
    gdock
    0.54
    <end_of_turn>
    0.53
    ችን
    0.53
    דה
    0.53
    reszt
    0.53
    POSITIVE LOGITS
     zone
    0.56
     to
    0.53
     we
    0.52
     p
    0.51
    ,
    0.51
     Kim
    0.50
     Mix
    0.49
     Zone
    0.48
     mix
    0.47
     Mount
    0.46
    Activations Density 0.000%

    No Known Activations