© 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. 165590
    Prev
    Next
    INDEX
    Explanations

    Drafts and changes

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

    comparing to original

    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
     предупре
    0.55
    гар
    0.46
     вас
    0.43
    ПР
    0.42
     혁
    0.42
    ла
    0.42
     ඔබ
    0.42
     तोड़
    0.41
    ಿದ್ದಾನೆ
    0.41
     людей
    0.41
    POSITIVE LOGITS
    ের
    0.50
    的同时
    0.45
    的基础
    0.45
     olig
    0.44
     Draft
    0.44
     ,
    0.44
     draft
    0.43
     entr
    0.43
     instrument
    0.42
     dell
    0.41
    Activations Density 0.001%

    No Known Activations