© 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. 16-GEMMASCOPE-2-RES-262K
    7. 118259
    Prev
    Next
    INDEX
    Explanations

    papyrus, willow, sparrow, aspen

    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
    in
    0.88
    र
    0.84
    i
    0.82
    er
    0.76
    At
    0.74
    म
    0.74
    Many
    0.74
    aping
    0.73
    د
    0.73
    ve
    0.71
    POSITIVE LOGITS
     tenha
    0.79
     prüfe
    0.75
     überprü
    0.68
     būti
    0.68
    ઢી
    0.68
     Kame
    0.67
     byť
    0.66
     glTexParameteri
    0.66
     Bereits
    0.66
     PlayerSelector
    0.64
    Activations Density 0.006%

    No Known Activations