© 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. 89958
    Prev
    Next
    INDEX
    Explanations

    comparison website

    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
     ב
    0.51
     influência
    0.51
     контакта
    0.50
     despacho
    0.49
     технику
    0.48
    ต
    0.48
     théorie
    0.47
     объекты
    0.46
    ก
    0.46
    衙
    0.46
    POSITIVE LOGITS
     consultations
    0.48
    RM
    0.47
    mosaic
    0.47
    RR
    0.45
    cyst
    0.45
     Andree
    0.45
     Group
    0.45
    HRS
    0.45
    Shock
    0.44
    AHN
    0.44
    Activations Density 0.000%

    No Known Activations