© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 229009
    Prev
    Next
    INDEX
    Explanations

    construction applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    жая
    0.54
     फते
    0.48
    젊
    0.48
    Joke
    0.47
     पत्
    0.46
    맵
    0.45
     молоды
    0.44
    人々
    0.44
    谛
    0.44
    髡
    0.44
    POSITIVE LOGITS
     teeth
    0.47
     prospectus
    0.47
     Ceylon
    0.45
     semester
    0.44
     passport
    0.44
     vor
    0.44
     Chevron
    0.44
     sustainable
    0.43
     cavern
    0.42
     thermometer
    0.42
    Activations Density 0.001%

    No Known Activations