© 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. 10608
    Prev
    Next
    INDEX
    Explanations

    name: followed by identifier

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

    name key: structured 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
     فونبیٹ
    0.57
    <unused2173>
    0.52
     відноси
    0.48
     unwell
    0.46
    ों
    0.46
     fittest
    0.44
     erreichte
    0.43
     আপনা
    0.43
     palavras
    0.43
    ୍
    0.43
    POSITIVE LOGITS
    करण
    0.68
    nam
    0.63
     name
    0.61
    setName
    0.60
    plate
    0.57
    name
    0.56
    myName
    0.55
     Name
    0.54
    geving
    0.54
    ститут
    0.52
    Activations Density 0.006%

    No Known Activations