© 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. 44423
    Prev
    Next
    INDEX
    Explanations

    after clause or sentence

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

    sentence ending punctuation

    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
     clés
    0.34
    츨
    0.32
     మరి
    0.32
    맟
    0.31
     pathlib
    0.30
    числи
    0.29
     stains
    0.29
     monomials
    0.29
     άλλο
    0.29
    מי
    0.29
    POSITIVE LOGITS
     This
    0.39
     However
    0.37
    <start_of_image>
    0.37
     Similarly
    0.35
     Be
    0.35
     The
    0.34
     It
    0.34
     But
    0.33
     That
    0.33
     A
    0.33
    Activations Density 0.131%

    No Known Activations