© 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. 55680
    Prev
    Next
    INDEX
    Explanations

    keep you alive

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

    doing, healing, offers, advice

    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
    麿
    0.46
     сра
    0.45
    énom
    0.44
     ควร
    0.44
     mempel
    0.43
    erah
    0.43
     chicago
    0.42
    💂
    0.42
    üng
    0.41
    agl
    0.40
    POSITIVE LOGITS
     ওষুধের
    0.52
    RE
    0.49
    SECRET
    0.47
    RELATIVE
    0.46
    LECT
    0.46
    actions
    0.44
    Press
    0.44
    في
    0.44
    concret
    0.44
    PRESS
    0.43
    Activations Density 0.000%

    No Known Activations