© 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. 204753
    Prev
    Next
    INDEX
    Explanations

    final amount

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

    code and personal ownership

    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
    込み
    0.49
    leqslant
    0.47
     됐
    0.46
    fread
    0.46
    کم
    0.46
    '')
    0.45
     आहार
    0.45
    グレー
    0.44
    ウェア
    0.44
    擺
    0.44
    POSITIVE LOGITS
    club
    0.49
    nt
    0.47
    colormap
    0.47
    blind
    0.45
    ball
    0.45
    Header
    0.45
    inflation
    0.44
    cardo
    0.43
    ILY
    0.42
    band
    0.42
    Activations Density 0.000%

    No Known Activations