© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178659
    Prev
    Next
    INDEX
    Explanations

    searching for pointers

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

    by an or a

    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
    ദ്ര
    0.49
     perny
    0.49
     rije
    0.49
     fuer
    0.48
     Struggles
    0.46
     operative
    0.46
    }"/>
    0.45
    薅
    0.43
     excel
    0.43
     lifecycle
    0.43
    POSITIVE LOGITS
    mouseover
    0.49
    omas
    0.45
    δία
    0.45
    oda
    0.43
    指导
    0.43
    ปรับ
    0.43
    调
    0.43
    ména
    0.43
    μαι
    0.42
    过滤
    0.42
    Activations Density 0.001%

    No Known Activations