© 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. 16-GEMMASCOPE-2-RES-262K
    7. 89250
    Prev
    Next
    INDEX
    Explanations

    higher-order functions

    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_16_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
     nostrils
    0.57
     inhomogeneities
    0.56
     ankles
    0.55
    獃
    0.54
     creases
    0.52
     keadaan
    0.51
     stát
    0.49
     ശ
    0.49
     spół
    0.49
     ricost
    0.49
    POSITIVE LOGITS
    <h1>
    0.60
    3
    0.57
    ра
    0.55
    다
    0.52
    2
    0.52
    oa
    0.51
    ுக்
    0.51
    ισμό
    0.51
    ма
    0.50
    beg
    0.50
    Activations Density 0.000%

    No Known Activations