© 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. 188621
    Prev
    Next
    INDEX
    Explanations

    default choice

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

    legal consequences and penalties

    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
    दे
    0.48
    月の
    0.47
     brazen
    0.47
    獗
    0.47
    imension
    0.45
    eroom
    0.45
    おはよう
    0.45
    رمی
    0.45
    ただし
    0.45
    長の
    0.44
    POSITIVE LOGITS
     ഉൾ
    0.47
     包括
    0.46
    v
    0.46
    éli
    0.46
     ž
    0.46
     多
    0.46
     تي
    0.45
     Cé
    0.45
     بو
    0.45
     transporte
    0.44
    Activations Density 0.000%

    No Known Activations