© 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. 58363
    Prev
    Next
    INDEX
    Explanations

    emerging growth company

    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
    ковь
    -1.55
    }$,
    -1.52
     TOO
    -1.45
    резать
    -1.44
    zept
    -1.44
    |$
    -1.42
    ]</
    -1.39
    ($__
    -1.38
     demokra
    -1.38
    AGAIN
    -1.38
    POSITIVE LOGITS
     on
    1.73
     these
    1.72
     that
    1.67
     what
    1.67
     their
    1.66
     apoio
    1.61
     some
    1.54
     only
    1.52
    <bos>
    1.52
     time
    1.48
    Activations Density 0.002%

    No Known Activations