© 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. 117397
    Prev
    Next
    INDEX
    Explanations

    after specific phrases or punctuation

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

    floods and human races

    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
    恶意
    0.52
    苡
    0.50
    والي
    0.49
    悝
    0.49
    因為
    0.49
    曾经
    0.47
    為
    0.47
    長
    0.47
    语音
    0.47
    非常
    0.47
    POSITIVE LOGITS
    clude
    0.49
    feitos
    0.49
    ¼
    0.49
     westward
    0.47
    ctuations
    0.47
    habitation
    0.47
    ateau
    0.47
    flood
    0.46
    flo
    0.46
    ctors
    0.46
    Activations Density 0.001%

    No Known Activations