© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22136
    Prev
    Next
    INDEX
    Explanations

    postscript content

    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
     –
    -1.98
     
    -1.70
    </h4>
    -1.55
     пациентов
    -1.55
     plongée
    -1.41
     -
    -1.39
    ти
    -1.36
    которые
    -1.32
     (
    -1.30
    r
    -1.27
    POSITIVE LOGITS
     we
    2.14
    你不要
    1.93
     this
    1.86
     می‌توانید
    1.75
     pérd
    1.75
    ০
    1.66
    都已经
    1.65
     kald
    1.63
    ícias
    1.63
    }%
    1.63
    Activations Density 0.015%

    No Known Activations