© 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. 149089
    Prev
    Next
    INDEX
    Explanations

    numbers and timeframes

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

    your, she, different, disclaimer, slate, depends

    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
    plist
    0.47
    ्रोत
    0.44
     narrower
    0.43
     unequivocal
    0.43
     larc
    0.42
     ভূমিক
    0.41
     wickets
    0.41
    ),]$
    0.41
     vulnerabilities
    0.40
    ณฑ์
    0.40
    POSITIVE LOGITS
    s
    0.63
    l
    0.55
    ෙ
    0.49
    b
    0.49
    z
    0.47
    ó
    0.47
    зино
    0.46
    m
    0.45
    ث
    0.45
    琛
    0.45
    Activations Density 0.000%

    No Known Activations