© 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. 213084
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    how you measuredeceptivelyformednarrative ofactually execute

    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
    3
    0.49
    6
    0.47
     elaborated
    0.46
     elucidated
    0.46
     interpolated
    0.44
    疲
    0.44
     articulated
    0.43
    友達
    0.42
    附加
    0.42
    徹
    0.42
    POSITIVE LOGITS
     价
    0.62
     одежда
    0.55
     baju
    0.54
     februari
    0.50
     защита
    0.50
     reiniciar
    0.49
     कीट
    0.48
     obnov
    0.46
     cuffs
    0.46
     फोटो
    0.45
    Activations Density 0.003%

    No Known Activations