© 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. 204401
    Prev
    Next
    INDEX
    Explanations

    holes

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

    given examples, previous list

    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
    u
    0.50
    uah
    0.48
     យើង
    0.48
     ausp
    0.45
     múltipl
    0.45
     উপর
    0.45
     قی
    0.45
     AMA
    0.44
     ama
    0.44
     மற்றொரு
    0.44
    POSITIVE LOGITS
    ቭ
    0.49
    Са
    0.46
    防御
    0.46
    Friend
    0.45
    бар
    0.45
    ennen
    0.45
    Avant
    0.44
    Б
    0.44
    操作
    0.44
    ೊಂಡ
    0.44
    Activations Density 0.001%

    No Known Activations