© 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. 89730
    Prev
    Next
    INDEX
    Explanations

    common words followed by punctuation

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

    greek god, pokemon, medieval village

    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
    పె
    0.48
     Versicherung
    0.47
     symmet
    0.47
     quantification
    0.46
     Quantification
    0.46
     Colombeau
    0.46
     మాత్రమే
    0.46
    癀
    0.46
     quantified
    0.45
    טר
    0.45
    POSITIVE LOGITS
     idea
    0.54
    Harold
    0.52
    xious
    0.48
    idea
    0.47
    ised
    0.45
    例えば
    0.45
    ↵
    0.45
    lain
    0.44
    掃除
    0.43
     Harold
    0.43
    Activations Density 0.000%

    No Known Activations