© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74536
    Prev
    Next
    INDEX
    Explanations

    within or virtual divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ார்க
    0.52
    љено
    0.48
    市场
    0.45
    талия
    0.45
    向き
    0.44
     limites
    0.44
    乔
    0.44
     شرطونو
    0.42
    ृता
    0.42
     требования
    0.42
    POSITIVE LOGITS
    ov
    0.45
    ï
    0.44
    halogen
    0.43
    }
    0.42
    ol
    0.42
    newline
    0.42
    newer
    0.41
     <
    0.41
    il
    0.40
    kin
    0.40
    Activations Density 0.003%

    No Known Activations