© 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. 33012
    Prev
    Next
    INDEX
    Explanations

    interact with prompts

    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
    law
    0.50
    ¾
    0.50
    icing
    0.47
    ward
    0.46
    bral
    0.45
    ph
    0.44
    Style
    0.44
    wage
    0.44
    jší
    0.43
    ť
    0.42
    POSITIVE LOGITS
     mysteries
    0.60
     culturais
    0.55
    큥
    0.54
     glomerul
    0.54
     daffodils
    0.54
     glories
    0.53
     neighborhoods
    0.52
     azi
    0.52
    టమి
    0.52
     Krzysz
    0.52
    Activations Density 0.000%

    No Known Activations