© 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. 145104
    Prev
    Next
    INDEX
    Explanations

    sequence of words leading to punctuation

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

    lists and explanations

    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
     सिंगल
    0.47
     மர
    0.46
    潾
    0.46
    州
    0.45
    珢
    0.45
    双
    0.44
    ệnh
    0.43
    requenz
    0.42
    禕
    0.42
    雙
    0.42
    POSITIVE LOGITS
    ר
    0.49
    at
    0.49
    le
    0.47
    interpreted
    0.47
    נד
    0.46
    qv
    0.45
    er
    0.44
    ius
    0.44
    byte
    0.44
    letter
    0.44
    Activations Density 0.001%

    No Known Activations