© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13729
    Prev
    Next
    INDEX
    Explanations

    running ancestor simulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglin
    0.49
    𝒌
    0.48
    વતી
    0.47
     இன்று
    0.47
    ilat
    0.47
    意识到
    0.47
    čiai
    0.47
    മ
    0.46
    Ꮙ
    0.46
     உடல்
    0.46
    POSITIVE LOGITS
    。
    0.49
    PP
    0.46
     cursor
    0.45
    ,
    0.45
    color
    0.44
    ES
    0.43
    GitHub
    0.43
    FV
    0.42
    cursor
    0.42
     customization
    0.42
    Activations Density 0.014%

    No Known Activations