© 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. 169720
    Prev
    Next
    INDEX
    Explanations

    minimizing or maximizing values

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

    minimize or maximize

    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
    させて
    0.47
    '
    0.43
    輸入
    0.42
    insert
    0.42
    -
    0.42
    truncate
    0.41
     dopln
    0.41
    tit
    0.40
    pays
    0.40
     ड्रॉप
    0.40
    POSITIVE LOGITS
     cuales
    0.50
    洴
    0.45
     dainty
    0.44
    цию
    0.43
     custod
    0.42
     decisão
    0.42
     époque
    0.41
    چھے
    0.41
     cliché
    0.41
    ButtonGroup
    0.41
    Activations Density 0.000%

    No Known Activations