© 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. 81089
    Prev
    Next
    INDEX
    Explanations

    quarter, style, jet

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

    skills needed for roles

    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
     døde
    0.52
    objeto
    0.52
     objeto
    0.47
    .],
    0.45
    अल
    0.45
     сколько
    0.45
     இன்றைய
    0.45
    நோய
    0.44
     objek
    0.44
    Contato
    0.44
    POSITIVE LOGITS
     hemic
    0.45
     typography
    0.44
     arty
    0.44
    に着
    0.44
     -
    0.43
    直線
    0.43
     cactus
    0.42
     preprocessing
    0.42
     clubhouse
    0.42
     presta
    0.42
    Activations Density 0.000%

    No Known Activations