© 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. 142736
    Prev
    Next
    INDEX
    Explanations

    commercial discretion

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

    not meeting

    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
    רה
    0.50
    LAS
    0.46
    ړو
    0.45
     сыгра
    0.44
    き
    0.43
    чили
    0.43
    چا
    0.43
    <0x89>
    0.43
     cocok
    0.43
    ्यान
    0.42
    POSITIVE LOGITS
    baden
    0.48
     ඉද
    0.45
    anta
    0.45
    ilan
    0.44
    itive
    0.44
     Neville
    0.44
     Physik
    0.43
    ining
    0.43
    asma
    0.43
     మొ
    0.43
    Activations Density 0.001%

    No Known Activations