© 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. 242092
    Prev
    Next
    INDEX
    Explanations

    back to, wall was, detailed box

    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
    г
    0.48
    ього
    0.46
     Daniels
    0.46
    開
    0.45
    ంచి
    0.45
    తీ
    0.45
    ‮
    0.44
    ла
    0.43
    дым
    0.43
     Lester
    0.43
    POSITIVE LOGITS
    bk
    0.49
    encephal
    0.48
     விதி
    0.48
     ROB
    0.47
     unilateral
    0.47
    idemargin
    0.47
    rawberry
    0.47
     dilatation
    0.47
     स्क्
    0.46
    increases
    0.46
    Activations Density 0.001%

    No Known Activations