© 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. 184037
    Prev
    Next
    INDEX
    Explanations

    forms after punctuation

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

    available to, dot to

    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
    lng
    0.54
    rt
    0.53
     symptoms
    0.49
    ':[
    0.49
     concentrations
    0.49
    ্জন
    0.47
    ']
    0.46
    le
    0.46
    htm
    0.46
    BeerItem
    0.45
    POSITIVE LOGITS
    ясь
    0.43
    대한
    0.42
     பணி
    0.42
     Josiah
    0.42
    ండా
    0.41
    요
    0.41
    ども
    0.41
    년을
    0.41
    ूले
    0.41
    用紙
    0.41
    Activations Density 0.000%

    No Known Activations