© 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. 133941
    Prev
    Next
    INDEX
    Explanations

    clash over, road rug, flexible plastic

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

    risk evaluation

    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
    EX
    0.53
    r
    0.52
    dropna
    0.50
    用途
    0.50
    AS
    0.49
    EST
    0.49
    a
    0.49
     つ
    0.48
    PP
    0.48
    ิร์
    0.47
    POSITIVE LOGITS
    郄
    0.49
    ၊
    0.47
     bầu
    0.47
     bav
    0.47
     philosophers
    0.47
    掂
    0.46
     theologians
    0.46
     otherworldly
    0.46
     calendars
    0.45
     amendments
    0.45
    Activations Density 0.000%

    No Known Activations