© 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. 120948
    Prev
    Next
    INDEX
    Explanations

    weeks will, project underway

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

    focus on application

    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
     verpflichtet
    0.52
     ပြော
    0.51
    తారు
    0.46
    ㄇ
    0.45
    ACION
    0.45
     うち
    0.45
    之内
    0.45
     말씀
    0.44
    AfterTax
    0.44
     電力
    0.44
    POSITIVE LOGITS
    s
    0.53
    ↵
    0.50
    add
    0.47
    w
    0.47
    canc
    0.46
    dip
    0.46
    roughly
    0.46
    as
    0.45
    es
    0.45
     to
    0.45
    Activations Density 0.000%

    No Known Activations