© 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. 43983
    Prev
    Next
    INDEX
    Explanations

    UK emergency contact

    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
    ‌
    0.49
    <strong>
    0.46
    🍂
    0.45
    한다
    0.44
    বাড়
    0.44
    🎃
    0.43
    contains
    0.43
    en
    0.43
    💨
    0.43
    ----------------
    0.42
    POSITIVE LOGITS
    стом
    0.53
     তারাও
    0.52
    มั่น
    0.51
    ین
    0.50
     মিটিং
    0.50
     mancanza
    0.49
     човек
    0.49
     их
    0.49
     ඔවුන්
    0.49
    谀
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.