© 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. 119944
    Prev
    Next
    INDEX
    Explanations

    job, candidates, save, quota, streak, schedule

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

    API processes

    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
     冷
    0.51
    䖝
    0.49
     Drift
    0.48
    伥
    0.48
     Motif
    0.48
    lıkla
    0.48
     Inglis
    0.47
    浃
    0.47
     Polaribacter
    0.46
     Accumulated
    0.46
    POSITIVE LOGITS
    粵
    0.46
    한
    0.45
    redit
    0.44
    Fragment
    0.42
    ocompat
    0.42
    透
    0.42
    하이
    0.41
    umann
    0.41
    tfine
    0.41
    사는
    0.40
    Activations Density 0.000%

    No Known Activations