© 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. 69171
    Prev
    Next
    INDEX
    Explanations

    lists and events

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

    getting labeled data

    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
    html
    0.55
    Q
    0.52
    G
    0.50
    ai
    0.49
    body
    0.49
    postcss
    0.49
    SZ
    0.49
    core
    0.48
    V
    0.48
    ipv
    0.47
    POSITIVE LOGITS
    名单
    0.56
     الطعام
    0.55
     liste
    0.50
     Grammy
    0.48
     бума
    0.47
     दोबारा
    0.46
     एनिमल
    0.46
    ्युनिकेशन
    0.45
    委员会
    0.44
     додат
    0.44
    Activations Density 0.001%

    No Known Activations