© 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. 106264
    Prev
    Next
    INDEX
    Explanations

    officers, firms, publisher

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

    ICT data fits

    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
     '',
    0.52
     avenues
    0.50
    otoxin
    0.49
     inhibition
    0.47
    pling
    0.47
    otoxic
    0.47
    ,
    0.46
     pathways
    0.45
    ranged
    0.45
    '',
    0.44
    POSITIVE LOGITS
    受験
    0.45
     budete
    0.45
     podnik
    0.45
    我們
    0.44
    誰
    0.44
    SDK
    0.44
    ━━━━
    0.44
    整個
    0.43
    類
    0.43
    懦
    0.43
    Activations Density 0.000%

    No Known Activations