© 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. 25588
    Prev
    Next
    INDEX
    Explanations

    ending quotes or punctuation

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

    quotation marks after periods

    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
     mout
    0.43
     murm
    0.43
     gelangen
    0.42
     nodded
    0.42
     muttered
    0.42
    咽
    0.41
     gasped
    0.41
     crammed
    0.41
     murmured
    0.40
     obstruct
    0.39
    POSITIVE LOGITS
    ått
    0.41
    आज
    0.39
    ">
    0.38
    ıma
    0.38
    ♎
    0.38
     Case
    0.38
     ‬
    0.38
     SRP
    0.37
    isma
    0.37
    There
    0.37
    Activations Density 0.010%

    No Known Activations