© 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. 192215
    Prev
    Next
    INDEX
    Explanations

    call to click

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

    array or list structures

    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
    腊
    0.50
    anesu
    0.49
     conseguido
    0.46
    温泉
    0.45
    ิน
    0.44
     giocando
    0.44
    鞄
    0.43
     circunstancias
    0.43
    ла
    0.42
     /^
    0.42
    POSITIVE LOGITS
    jsdel
    0.44
    ick
    0.42
     retrofit
    0.42
    est
    0.42
    విద్య
    0.42
    wym
    0.41
    edk
    0.41
    cfm
    0.41
    CFT
    0.41
    ites
    0.41
    Activations Density 0.000%

    No Known Activations