© 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. 116868
    Prev
    Next
    INDEX
    Explanations

    seen in differentleader andgems.or withoutfor thedepo prohis thoughtview thatmonitoring has

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

    monitoring and regulations

    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
    in
    0.49
    冈
    0.49
    ing
    0.47
    不用
    0.44
    inie
    0.44
    otia
    0.43
    锣
    0.43
    inę
    0.42
     ہیں
    0.41
    ingi
    0.41
    POSITIVE LOGITS
     сег
    0.49
    И
    0.45
    들이
    0.45
    दात
    0.45
    Ре
    0.43
     thickly
    0.42
    কেউ
    0.42
    사이
    0.41
    groupID
    0.41
    Dataset
    0.41
    Activations Density 0.000%

    No Known Activations