© 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. 79042
    Prev
    Next
    INDEX
    Explanations

    Ten Meritorious Acts

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

    listing roles or components

    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
    examtype
    0.47
    ياه
    0.45
    멈
    0.44
    뚫
    0.44
    doch
    0.43
    ultz
    0.43
     চট্ট
    0.42
    接到
    0.42
    McL
    0.42
     காண
    0.42
    POSITIVE LOGITS
     SN
    0.52
     severity
    0.48
     mucous
    0.48
     Caution
    0.48
     Priyanka
    0.46
     Pud
    0.46
     WHICH
    0.46
     ↓
    0.45
     MeOH
    0.45
     Oud
    0.45
    Activations Density 0.001%

    No Known Activations