© 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. 224717
    Prev
    Next
    INDEX
    Explanations

    listing conjunctions and punctuation

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

    languages

    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
    isti
    0.46
    態度
    0.44
    +/-
    0.44
    πού
    0.44
     velocities
    0.43
    giants
    0.42
    finance
    0.42
    dade
    0.42
    callow
    0.42
    aggressive
    0.42
    POSITIVE LOGITS
     Hsu
    0.51
     walked
    0.50
     즉
    0.49
    ，
    0.47
     ಥ
    0.47
     Enlightenment
    0.47
     photographed
    0.46
    ש
    0.46
     Tsuk
    0.46
     cytoskeleton
    0.46
    Activations Density 0.000%

    No Known Activations