© 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. 163022
    Prev
    Next
    INDEX
    Explanations

    language-non-english

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

    manual actions and technical terms

    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
     conventionally
    0.45
     nascent
    0.44
    דר
    0.43
    ви
    0.42
    פתח
    0.42
    ד
    0.41
    エレ
    0.41
    מין
    0.41
     articul
    0.40
    여러분
    0.40
    POSITIVE LOGITS
     মেনে
    0.46
     ķ
    0.45
    作出
    0.45
    ındadır
    0.45
     agir
    0.44
     Sardar
    0.44
     blieb
    0.44
    ailangan
    0.44
     त्रिज्या
    0.44
     hong
    0.43
    Activations Density 0.000%

    No Known Activations