© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71990
    Prev
    Next
    INDEX
    Explanations

    dismissing possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -1.43
     many
    -1.41
     any
    -1.38
     this
    -1.29
     more
    -1.26
     on
    -1.23
    From
    -1.16
    www
    -1.16
     without
    -1.12
     meisten
    -1.12
    POSITIVE LOGITS
     possibility
    1.41
     possib
    1.35
     ‚
    1.30
     พร้อม
    1.24
    ्ञ
    1.24
    ఽ
    1.21
     «
    1.20
    arrive
    1.19
    鹇
    1.18
     possibilities
    1.17
    Activations Density 0.041%

    No Known Activations