© 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. 25726
    Prev
    Next
    INDEX
    Explanations

    browser name instructions

    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
    0.61
    ca
    0.58
    ↵
    0.52
    ↵↵
    0.48
    x
    0.48
    th
    0.47
    c
    0.46
    v
    0.45
     storm
    0.43
     radii
    0.43
    POSITIVE LOGITS
    刓
    0.52
     CustB
    0.46
     !)
    0.45
    +#+#
    0.44
     아멘
    0.44
     Elytres
    0.44
    洽
    0.44
     És
    0.43
     mulher
    0.43
     faiblement
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.