© 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. 22-GEMMASCOPE-RES-131K
    7. 15320
    Prev
    Next
    INDEX
    Explanations

    me followed by information-seeking words

    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_22/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
     Some
    -1.78
     There
    -1.75
     Many
    -1.63
    Several
    -1.63
    Those
    -1.62
    }$.
    -1.53
    ).
    -1.53
    There
    -1.52
    Three
    -1.52
    Many
    -1.50
    POSITIVE LOGITS
     that
    2.44
     how
    2.34
     about
    2.05
    がなく
    1.93
     why
    1.84
     campeón
    1.80
     recente
    1.78
     geogra
    1.76
    注意事
    1.72
     icona
    1.71
    Activations Density 0.022%

    No Known Activations