© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1933
    Prev
    Next
    INDEX
    Explanations

    text and images

    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_40_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
    アウト
    0.41
    Cxx
    0.41
    iph
    0.40
    番
    0.40
    Sau
    0.39
    input
    0.38
    ToBounds
    0.38
     wewnętr
    0.37
    下来的
    0.37
    唯一
    0.37
    POSITIVE LOGITS
     global
    0.43
     databases
    0.41
     scraped
    0.40
     punct
    0.40
     legible
    0.40
     cooked
    0.38
     vert
    0.37
     Age
    0.37
    丳
    0.37
     age
    0.37
    Activations Density 0.016%

    No Known Activations