© 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. 34-GEMMASCOPE-RES-131K
    7. 2472
    Prev
    Next
    INDEX
    Explanations

    sponsor or partner

    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_34/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
     دیگران
    -0.83
     geográfica
    -0.76
    κίνη
    -0.73
     grasshopper
    -0.73
     terecht
    -0.72
    Identifiers
    -0.72
    })]
    -0.72
    YER
    -0.71
     AssemblyCulture
    -0.71
    assertions
    -0.71
    POSITIVE LOGITS
     sponsor
    3.91
     sponsors
    3.88
    sponsor
    2.86
     sponsoring
    2.80
     Sponsor
    2.77
     Sponsors
    2.67
     sponsorship
    2.64
    Sponsors
    2.53
    Sponsor
    2.48
     SPONS
    2.47
    Activations Density 0.039%

    No Known Activations