© 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. 217191
    Prev
    Next
    INDEX
    Explanations

    sentence start punctuation

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

    lists and bullet points

    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
    http
    0.58
     Science
    0.54
    ↵↵
    0.52
    <strong>
    0.51
     Writing
    0.48
     Christian
    0.47
     David
    0.47
    <em>
    0.46
     University
    0.46
     Steven
    0.46
    POSITIVE LOGITS
     проєкту
    0.58
     २०२
    0.55
     onboarding
    0.54
    ୍କ
    0.53
    sailboat
    0.52
    kfollowers
    0.51
     dropdown
    0.51
     sequência
    0.50
     проє
    0.50
     rollerskates
    0.50
    Activations Density 0.099%

    No Known Activations