© 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. 50743
    Prev
    Next
    INDEX
    Explanations

    following this layer

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

    safety requirement

    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
     عناصر
    0.45
    كم
    0.45
    Forest
    0.44
    狩
    0.44
    动力
    0.43
     څرنګوالی
    0.43
     mécanismes
    0.43
    禹
    0.43
    掝
    0.43
    ร์
    0.43
    POSITIVE LOGITS
     extensively
    0.55
     being
    0.53
     tense
    0.52
     have
    0.52
     excessively
    0.52
     tls
    0.52
     inset
    0.50
     to
    0.49
     well
    0.49
     trigon
    0.49
    Activations Density 0.000%

    No Known Activations