© 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. 73200
    Prev
    Next
    INDEX
    Explanations

    temperature and intensity

    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
     It
    -1.77
     actitudes
    -1.67
     Puede
    -1.66
     she
    -1.63
     puede
    -1.59
     ľ
    -1.52
    噥
    -1.52
    それ
    -1.51
     religiosos
    -1.48
    ῖν
    -1.48
    POSITIVE LOGITS
    𝟱
    1.66
     meliputi
    1.53
    ization
    1.48
    ↵↵↵
    1.46
     altes
    1.44
     網
    1.40
    鞴
    1.35
     mewakili
    1.34
    过后
    1.34
     goi
    1.34
    Activations Density 0.009%

    No Known Activations