© 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. 238346
    Prev
    Next
    INDEX
    Explanations

    speaking the language

    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
     Verhalten
    0.52
    চ
    0.51
    рма
    0.50
    日期
    0.49
    вак
    0.49
     Interesse
    0.48
    㕲
    0.48
    栽培
    0.47
    之人
    0.47
    Одна
    0.46
    POSITIVE LOGITS
    ell
    0.61
    ived
    0.57
    ird
    0.56
    elling
    0.54
    elles
    0.54
    ells
    0.54
    aded
    0.54
    ince
    0.52
    ons
    0.51
    enn
    0.51
    Activations Density 0.000%

    No Known Activations