© 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. 160095
    Prev
    Next
    INDEX
    Explanations

    places and populations

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

    `setup()` functions and code completion

    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
     책
    0.46
     በጥ
    0.46
     보
    0.43
    するとき
    0.40
    Either
    0.40
     스프
    0.40
    ിട
    0.40
    ましょう
    0.40
    Too
    0.39
    tey
    0.39
    POSITIVE LOGITS
     habitantes
    0.56
    ◸
    0.54
    обу
    0.52
    eosin
    0.52
     numerosas
    0.51
     naciones
    0.50
    عبير
    0.50
     entero
    0.49
    ليك
    0.49
     inhabited
    0.49
    Activations Density 0.000%

    No Known Activations