© 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. 57725
    Prev
    Next
    INDEX
    Explanations

    phrases and their common follow-ups

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

    looking for, portraits, precisely, fortress, write

    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
    嘤
    0.50
     দাঁ
    0.50
     پرورش
    0.49
    哪个
    0.48
     জোর
    0.47
     दहा
    0.46
     Cantonese
    0.46
     ausführ
    0.45
    底下
    0.45
    bottomMargin
    0.43
    POSITIVE LOGITS
    พ
    0.56
    I
    0.50
     initiation
    0.48
     heterogeneity
    0.46
    TOR
    0.46
    విత
    0.46
    FIELD
    0.45
    M
    0.45
     stewardship
    0.45
     millennia
    0.45
    Activations Density 0.000%

    No Known Activations