© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66837
    Prev
    Next
    INDEX
    Explanations

    Seeing the title

    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
    ability
    -1.42
    albeit
    -1.34
    掂
    -1.31
    otherwise
    -1.30
     redus
    -1.30
     fero
    -1.30
     relativi
    -1.30
    tais
    -1.28
    ing
    -1.28
    essing
    -1.27
    POSITIVE LOGITS
     from
    1.91
     and
    1.73
     at
    1.55
     abiertas
    1.42
     aisladas
    1.36
     should
    1.35
     volver
    1.34
     would
    1.33
     The
    1.31
     Those
    1.27
    Activations Density 0.015%

    No Known Activations