© 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. 154325
    Prev
    Next
    INDEX
    Explanations

    any box or venue

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

    not followed by a contrast

    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
    ה
    0.50
     Delegates
    0.48
     Delicious
    0.47
     donnant
    0.47
     influential
    0.47
    一切
    0.46
    ார்
    0.46
    喈
    0.46
    紀錄
    0.46
     Gains
    0.45
    POSITIVE LOGITS
     chitosan
    0.51
    PubMed
    0.48
     けど
    0.46
     препарат
    0.46
    Pare
    0.44
    평
    0.43
    HEL
    0.43
     pare
    0.42
    럭
    0.42
     ਦਵਾਈ
    0.42
    Activations Density 0.000%

    No Known Activations