© 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. 112067
    Prev
    Next
    INDEX
    Explanations

    party, sewing, assignments, patterns

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

    program definition and serial dilution

    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
    νού
    0.54
    γεν
    0.53
    🔮
    0.50
     चित्र
    0.46
    তাম
    0.46
     푸
    0.45
    numericUpDown
    0.45
    🥧
    0.45
    🍧
    0.45
    ♓
    0.44
    POSITIVE LOGITS
    ي
    0.56
    મ
    0.56
     clinics
    0.49
     मरीज
    0.45
     Sancho
    0.44
    り
    0.43
    ',
    0.42
     DQ
    0.41
    ित्य
    0.41
    lobby
    0.41
    Activations Density 0.000%

    No Known Activations