© 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. 17404
    Prev
    Next
    INDEX
    Explanations

    space between

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

    symbols used as separators

    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
    ח
    0.47
    מ
    0.46
    Spanish
    0.42
    о
    0.41
     জাতিসংঘের
    0.40
     Здесь
    0.39
     biennium
    0.39
     disini
    0.39
    ത്തിന്റെയും
    0.39
     مقابلہ
    0.38
    POSITIVE LOGITS
    唛
    0.42
     ними
    0.41
    getNumber
    0.41
     }-
    0.39
    TNumber
    0.38
     depo
    0.37
     yazı
    0.37
     beneficiaries
    0.36
     arrêter
    0.36
    ઠવા
    0.36
    Activations Density 0.000%

    No Known Activations