© 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. 114105
    Prev
    Next
    INDEX
    Explanations

    finding a good fit

    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
    Negative Logits
     étoile
    -1.48
     racines
    -1.47
     vingt
    -1.38
    
    -1.38
     changements
    -1.36
     roues
    -1.36
     visites
    -1.35
     komplet
    -1.34
     namen
    -1.32
     amie
    -1.31
    POSITIVE LOGITS
     that
    2.19
     especially
    1.88
     about
    1.75
     how
    1.71
     with
    1.70
     or
    1.66
    }$.
    1.55
     particularly
    1.53
     may
    1.52
     where
    1.45
    Activations Density 0.125%

    No Known Activations