© 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. 34702
    Prev
    Next
    INDEX
    Explanations

    status, employment, modules, today

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

    documentation, system, devices, sequence, '*'

    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
     sard
    0.46
     generations
    0.46
     heightened
    0.45
     दुर्गा
    0.44
     nationalist
    0.44
     jog
    0.42
     knife
    0.41
    ḿ
    0.41
     config
    0.41
     pila
    0.41
    POSITIVE LOGITS
    Setelah
    0.50
    ）・
    0.46
    鈳
    0.46
     Bundan
    0.46
     ડિઝ
    0.45
    或者是
    0.44
     করেনি
    0.44
    zaXRvcn
    0.44
    VH
    0.43
    成了
    0.43
    Activations Density 0.000%

    No Known Activations