© 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. 247985
    Prev
    Next
    INDEX
    Explanations

    child or daughter relationships

    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
    ட்டி
    0.49
    until
    0.49
    鞄
    0.46
    يو
    0.45
    楽器
    0.44
    う
    0.43
    ደበ
    0.43
     ತಮ್ಮ
    0.43
    ਜੀ
    0.43
     ভাষা
    0.42
    POSITIVE LOGITS
    ir
    0.53
    ;
    0.53
     cre
    0.50
    :
    0.50
     PHILLIPS
    0.49
     者
    0.48
     Proceed
    0.48
    :}
    0.47
     memorable
    0.47
     müm
    0.47
    Activations Density 0.000%

    No Known Activations