© 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. 52466
    Prev
    Next
    INDEX
    Explanations

    bed frame with storage

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

    justified by, English (, other planets

    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
    話し
    0.52
     звер
    0.46
    ColumnKind
    0.43
     変
    0.43
    Ⲉ
    0.42
     диапа
    0.42
     certain
    0.41
     underground
    0.41
     monkeys
    0.41
     Kyrgyz
    0.41
    POSITIVE LOGITS
    óis
    0.48
     اسمبلی
    0.47
     Claims
    0.44
    ణులు
    0.43
    claims
    0.43
     idam
    0.43
    á
    0.41
    仆
    0.41
     precis
    0.41
    attes
    0.41
    Activations Density 0.000%

    No Known Activations