© 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-16K
    7. 13114
    Prev
    Next
    INDEX
    Explanations

    foot movement

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

    multiplication operations or recipes

    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_16k_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
     sparkles
    0.55
     sparkle
    0.47
     Fractals
    0.46
     evanescent
    0.44
    🫧
    0.44
     wav
    0.43
     sparkly
    0.42
     fade
    0.42
     flattened
    0.42
     स्थित
    0.41
    POSITIVE LOGITS
    📗
    0.45
    comand
    0.44
    Verlag
    0.42
    Guide
    0.42
    📔
    0.42
    chette
    0.40
    cols
    0.40
    Chunk
    0.39
    Lead
    0.39
    HIST
    0.39
    Activations Density 0.103%

    No Known Activations