© 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. 200128
    Prev
    Next
    INDEX
    Explanations

    mentioning users

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

    email greetings and mentions

    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
     commenting
    0.47
     explique
    0.45
    ꧁
    0.42
    ?!
    0.41
    ?!?
    0.41
     pretending
    0.41
    ?!?!
    0.41
    评论
    0.41
     contradicted
    0.41
     disagreed
    0.40
    POSITIVE LOGITS
    чені
    0.46
    ार
    0.46
     tutte
    0.45
    EDE
    0.45
    ют
    0.44
    ет
    0.44
    ented
    0.44
    лась
    0.44
    ற
    0.44
    aditional
    0.44
    Activations Density 0.004%

    No Known Activations