© 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. 9026
    Prev
    Next
    INDEX
    Explanations

    describing a process or characteristic

    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
    Not in Any Lists

    No Comments

    Negative Logits
    시장
    0.18
     prince
    0.18
     و
    0.18
     ו
    0.18
    า
    0.18
    愍
    0.17
     demás
    0.17
     spie
    0.17
    ་
    0.17
     habitation
    0.17
    POSITIVE LOGITS
     extremely
    0.23
     using
    0.20
     optional
    0.20
     brainstorming
    0.20
    not
    0.19
     centrifugation
    0.19
     two
    0.19
     eine
    0.19
     autofocus
    0.19
     extrêmement
    0.19
    Activations Density 0.287%

    No Known Activations