© 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. 227159
    Prev
    Next
    INDEX
    Explanations

    repertoire, tracer, century, pad

    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
    tait
    0.47
    тья
    0.46
    AddModelError
    0.43
    鹑
    0.42
    गांव
    0.39
    맇
    0.39
    Pair
    0.39
    ضو
    0.38
     svojih
    0.38
    вают
    0.38
    POSITIVE LOGITS
     নভেম্বর
    0.49
     ata
    0.47
    ે
    0.47
     basically
    0.46
     চির
    0.45
    urus
    0.44
     by
    0.44
    rents
    0.44
     czyli
    0.43
    NSDictionary
    0.43
    Activations Density 0.001%

    No Known Activations