© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55777
    Prev
    Next
    INDEX
    Explanations

    time, neat, dreams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.63
     Green
    0.49
    Green
    0.46
     C
    0.46
     Cri
    0.46
     Griffith
    0.43
     Bri
    0.41
    <0xC2>
    0.41
     Prince
    0.41
     Rum
    0.40
    POSITIVE LOGITS
     jadwal
    0.52
    的其他
    0.49
     televised
    0.48
     যারা
    0.48
     예배
    0.48
     равномер
    0.47
     adhere
    0.47
     dvara
    0.46
    দেব
    0.46
     sparsebundle
    0.46
    Activations Density 0.005%

    No Known Activations