© 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. 178515
    Prev
    Next
    INDEX
    Explanations

    0:00 timestamps

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

    chat, diligence, steps

    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
    <h5>
    0.57
    <h4>
    0.50
    AR
    0.48
    Runner
    0.46
    <h6>
    0.46
    Art
    0.44
    IT
    0.43
    ৯৫
    0.40
    +
    0.40
    ar
    0.39
    POSITIVE LOGITS
     credo
    0.46
     구
    0.45
    quête
    0.44
    äume
    0.41
    ब्लिक
    0.40
    бере
    0.40
     creed
    0.39
     ми
    0.39
    tochy
    0.39
     фар
    0.38
    Activations Density 0.000%

    No Known Activations