© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137677
    Prev
    Next
    INDEX
    Explanations

    not and optional

    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
    impact
    0.52
    brane
    0.52
    holes
    0.50
    ssc
    0.47
    terus
    0.47
     Chubb
    0.47
    轂
    0.46
    cookie
    0.46
    ind
    0.46
    Butyl
    0.46
    POSITIVE LOGITS
     อย่า
    0.45
     unul
    0.44
     zodat
    0.43
    ى
    0.43
    ılan
    0.43
     tricky
    0.43
     Portanto
    0.43
     เดิน
    0.42
     منشور
    0.42
    ovski
    0.42
    Activations Density 0.005%

    No Known Activations