© 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. 193208
    Prev
    Next
    INDEX
    Explanations

    rubbish, produced, time, rubbish, allows, law

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

    text completion and relationship stages

    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
    Hiro
    0.50
    M
    0.47
    Rack
    0.46
    Robot
    0.46
    行った
    0.46
    CUDA
    0.46
    AIN
    0.45
    Practical
    0.45
    ेला
    0.45
    Samuel
    0.45
    POSITIVE LOGITS
     oscillations
    0.50
     خصوص
    0.50
     autoch
    0.49
    </h2>
    0.48
     unaffected
    0.48
     substrates
    0.47
     גר
    0.47
     surm
    0.47
    ancellation
    0.47
    ಸ್
    0.46
    Activations Density 0.000%

    No Known Activations