© 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. 233147
    Prev
    Next
    INDEX
    Explanations

    designed to, Night Fall, data storage

    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
    izações
    0.53
    esses
    0.47
    UME
    0.45
    pares
    0.45
    KD
    0.43
    armen
    0.43
    GQ
    0.42
    瀨
    0.42
    ume
    0.42
    ಧ್ಯ
    0.42
    POSITIVE LOGITS
    取出
    0.47
     berarti
    0.46
     हीरा
    0.46
     Mfg
    0.46
     estampado
    0.46
     Merino
    0.45
     korist
    0.44
     irreg
    0.44
     wygl
    0.44
     instalado
    0.42
    Activations Density 0.001%

    No Known Activations