© 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. 127558
    Prev
    Next
    INDEX
    Explanations

    custom orders

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

    actions in technical contexts

    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
    2
    0.50
    л
    0.50
    ർ
    0.50
    ﺨ
    0.47
    4
    0.46
    संयुक्त
    0.45
    <b>
    0.45
     discounted
    0.44
    ப்பிய
    0.44
     memos
    0.44
    POSITIVE LOGITS
     那麼
    0.53
    lassen
    0.53
    eful
    0.50
     ©️
    0.48
    tte
    0.47
    gels
    0.47
    chelle
    0.46
    बिट
    0.46
     অতিথি
    0.46
     μέσα
    0.46
    Activations Density 0.000%

    No Known Activations