© 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. 233071
    Prev
    Next
    INDEX
    Explanations

    providers ALL

    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
     Supremo
    0.45
    Computational
    0.45
    తాయి
    0.43
    🥰
    0.43
    StudioProjects
    0.42
    ྲ
    0.42
    合适
    0.40
     Saat
    0.40
    羡
    0.40
    Corner
    0.40
    POSITIVE LOGITS
    qc
    0.53
    white
    0.52
     fastest
    0.49
     inov
    0.48
     whites
    0.48
     direc
    0.48
     innovate
    0.47
     wines
    0.47
     usb
    0.46
    qualified
    0.46
    Activations Density 0.002%

    No Known Activations