© 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. 90236
    Prev
    Next
    INDEX
    Explanations

    official meetings

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

    structure or advice

    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
    ,|\
    0.54
    стью
    0.53
     योजनाओं
    0.50
    .,"
    0.49
    醂
    0.48
    dört
    0.48
    September
    0.48
    October
    0.48
    沃尔
    0.47
    |।
    0.47
    POSITIVE LOGITS
     unsupported
    0.50
    batas
    0.49
     vip
    0.48
     VIP
    0.48
     Miser
    0.47
     tua
    0.46
     Aspect
    0.46
     technician
    0.45
     trainee
    0.45
     diploma
    0.44
    Activations Density 0.000%

    No Known Activations