© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31748
    Prev
    Next
    INDEX
    Explanations

    code generation contexts

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    el
    0.46
    durch
    0.44
    <0x0C>
    0.41
    names
    0.40
    this
    0.39
    dzie
    0.39
    onter
    0.39
    Message
    0.38
    Search
    0.38
    methods
    0.38
    POSITIVE LOGITS
     fuelled
    0.40
     oatmeal
    0.40
     അങ്ങനെ
    0.38
     गोवि
    0.36
     impuestos
    0.36
     fabricate
    0.36
     लिया
    0.36
    ︵
    0.36
     diabetics
    0.36
     aesthetic
    0.35
    Activations Density 0.001%

    No Known Activations