© 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. 185052
    Prev
    Next
    INDEX
    Explanations

    newborn photo session

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

    bull market

    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
    Negative Logits
     excitatory
    0.49
    ین
    0.45
     উৎসাহ
    0.44
    ToolStripItem
    0.44
    য়েড
    0.44
    ("{
    0.44
     дописа
    0.43
     arrhythmia
    0.43
     бясплат
    0.42
     справа
    0.42
    POSITIVE LOGITS
     يست
    0.46
     चिह्नित
    0.45
     trifling
    0.45
     blamed
    0.42
     crashed
    0.42
    ନ
    0.41
     busted
    0.40
    聽
    0.40
    搗
    0.40
     melden
    0.40
    Activations Density 0.000%

    No Known Activations