© 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. 180788
    Prev
    Next
    INDEX
    Explanations

    legitimate interestlasting impressionmedical repatriation

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

    exploring new ways

    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
    RACT
    0.50
     March
    0.47
     रिमाइंडर
    0.46
    Օ
    0.46
     aynı
    0.46
    જે
    0.46
    ﯽ
    0.46
    Ó
    0.45
     ভাগের
    0.45
    ের
    0.45
    POSITIVE LOGITS
    o
    0.47
    u
    0.46
     stink
    0.44
     proble
    0.43
    producing
    0.43
     plausible
    0.43
     bug
    0.42
     interv
    0.42
     simpt
    0.41
    quartz
    0.40
    Activations Density 0.001%

    No Known Activations