© 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. 130760
    Prev
    Next
    INDEX
    Explanations

    share their obligations

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

    code debugging

    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
     cool
    0.49
     not
    0.47
    a
    0.45
     leftover
    0.45
     cools
    0.45
     spaced
    0.44
     noodle
    0.44
     landing
    0.44
     functional
    0.43
     conject
    0.43
    POSITIVE LOGITS
    getBlueTeam
    0.50
    壓縮
    0.48
    سه
    0.48
    ालय
    0.47
    昅
    0.47
    getSeconds
    0.46
    ത്തെ
    0.46
    俔
    0.45
    ри
    0.45
    陬
    0.45
    Activations Density 0.002%

    No Known Activations