© 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. 191661
    Prev
    Next
    INDEX
    Explanations

    ice cream sandwich

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

    understand why

    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
     releases
    0.43
     plików
    0.42
     wrappers
    0.42
    之后
    0.42
    ⵕ
    0.42
     வெளியிட்டு
    0.42
    sendKeys
    0.41
    อร
    0.41
    拍摄
    0.41
     인해
    0.41
    POSITIVE LOGITS
    िप
    0.51
    жим
    0.51
    тном
    0.49
    рт
    0.49
    й
    0.47
    чна
    0.47
    тна
    0.46
    ੍ਹਾਂ
    0.46
    ân
    0.46
    рг
    0.46
    Activations Density 0.000%

    No Known Activations