© 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. 5136
    Prev
    Next
    INDEX
    Explanations

    clamped color values between zero and one

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

    values between 0 and 1

    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
     бекер
    0.62
    俱乐
    0.62
     незакон
    0.56
    娼
    0.56
    谗
    0.55
     председа
    0.54
    setRequest
    0.53
    讒
    0.53
    azał
    0.52
     소개
    0.52
    POSITIVE LOGITS
     grayscale
    0.91
     values
    0.87
     scaling
    0.85
     normalization
    0.84
     pixel
    0.82
     normalized
    0.82
     pixels
    0.80
     smoothing
    0.80
     max
    0.80
     gradient
    0.80
    Activations Density 0.014%

    No Known Activations