© 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. 189368
    Prev
    Next
    INDEX
    Explanations

    particular circumstances

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

    complex tasks

    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
    upport
    0.49
    𝒍
    0.47
    =$(
    0.46
    unakan
    0.44
    "^
    0.44
    imageId
    0.44
    ાય
    0.43
    лой
    0.42
    unay
    0.42
    orted
    0.42
    POSITIVE LOGITS
    突然
    0.48
     aange
    0.46
     لتح
    0.46
    爯
    0.42
     Vals
    0.42
     Lehenga
    0.42
    デン
    0.41
     mittlerweile
    0.40
     kvůli
    0.40
     tiempos
    0.40
    Activations Density 0.002%

    No Known Activations