© 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. 122936
    Prev
    Next
    INDEX
    Explanations

    family names or full names

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

    open weights model

    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
     discrep
    0.52
     discrepancy
    0.46
     uop
    0.46
    ("%
    0.45
    中間
    0.45
    翁
    0.45
     rispond
    0.43
    什
    0.43
    一部分
    0.43
     indisc
    0.42
    POSITIVE LOGITS
    familyName
    0.52
    fullname
    0.51
     யான
    0.50
    se
    0.50
    फुल
    0.47
    ুল
    0.46
    හැ
    0.46
     गुस्
    0.46
    rin
    0.46
    murder
    0.46
    Activations Density 0.000%

    No Known Activations