© 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. 45675
    Prev
    Next
    INDEX
    Explanations

    more and bigger

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

    mitosis, wetness, schedule, Plakinastrella, IP, operations

    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
    l
    0.62
    *
    0.53
    i
    0.48
    iet
    0.47
    <0x0D>
    0.46
    ar
    0.45
     be
    0.45
    iven
    0.45
     covenant
    0.44
     fear
    0.44
    POSITIVE LOGITS
    taught
    0.55
     maquin
    0.50
    बाइल
    0.48
    सबुक
    0.48
     instruções
    0.48
    Ᏺ
    0.47
    شنبه
    0.47
    वियस
    0.47
    മ്പി
    0.47
    ාවිත
    0.47
    Activations Density 0.000%

    No Known Activations