© 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. 164120
    Prev
    Next
    INDEX
    Explanations

    USB drives

    np_acts-logits-general · gemini-2.5-flash-lite

    short duration or after episodes

    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
     Louie
    0.49
     軽量
    0.49
     brainstorm
    0.48
     😂
    0.47
     Internation
    0.46
     zl
    0.45
     dela
    0.45
     已
    0.44
     zespo
    0.44
    toUpperCase
    0.44
    POSITIVE LOGITS
    г
    0.51
    این
    0.51
    رید
    0.50
    ην
    0.49
    ар
    0.47
    િવસે
    0.47
    蕨
    0.46
    یسر
    0.46
    ја
    0.46
    дается
    0.46
    Activations Density 0.000%

    No Known Activations