© 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. 219504
    Prev
    Next
    INDEX
    Explanations

    foreign and technical terms

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

    sleek and

    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
    idum
    0.44
    yla
    0.43
    ብሰ
    0.43
    iveau
    0.42
    //}
    0.41
    yle
    0.41
    aza
    0.41
    ಿಸಿ
    0.41
    葡萄
    0.39
    PRS
    0.39
    POSITIVE LOGITS
     যাঁ
    0.49
    AssetsRequest
    0.46
     overdraft
    0.44
    ineri
    0.43
     سند
    0.42
    陴
    0.42
     সম্প
    0.42
    స్థ
    0.42
     enteral
    0.42
    plural
    0.41
    Activations Density 0.001%

    No Known Activations