© 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. 38147
    Prev
    Next
    INDEX
    Explanations

    measurement and description

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

    construct options for users

    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
    :>
    0.50
    hg
    0.46
     shortage
    0.46
     immigrant
    0.45
    :...
    0.45
     मोठ्या
    0.45
    เมล
    0.44
     بزرگ
    0.44
     הג
    0.44
    HG
    0.44
    POSITIVE LOGITS
    calcular
    0.46
    ンドウ
    0.44
     demuestra
    0.43
    ŕ
    0.43
     Observ
    0.42
    четов
    0.41
     utilizan
    0.41
     AWAY
    0.40
     Fungsi
    0.40
    inais
    0.40
    Activations Density 0.000%

    No Known Activations