© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38980
    Prev
    Next
    INDEX
    Explanations

    Gothic literature, prime number, blog corridor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Untold
    0.52
     أغ
    0.50
     autumnal
    0.48
    跶
    0.46
     eagles
    0.45
     boven
    0.44
    opolar
    0.44
    秋
    0.44
    ück
    0.43
     Grenz
    0.43
    POSITIVE LOGITS
    від
    0.52
    ಣಿ
    0.48
    лян
    0.47
    णिज्य
    0.45
     scintillation
    0.44
    শুধ
    0.44
    ハウス
    0.43
    鎬
    0.43
    ну
    0.42
    defines
    0.42
    Activations Density 0.001%

    No Known Activations