© 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. 40-GEMMASCOPE-2-RES-262K
    7. 219944
    Prev
    Next
    INDEX
    Explanations

    locations of

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    KURZBESCHREIBUNG
    0.41
     económica
    0.38
    ेंद
    0.38
    बे
    0.38
    安定
    0.38
    낮
    0.37
    ຶ
    0.37
    好吃
    0.37
     бесплатно
    0.37
     ]]
    0.37
    POSITIVE LOGITS
    FindAction
    0.44
    纰
    0.40
    webstore
    0.39
    codingPath
    0.38
     നിങ്ങൾക്ക്
    0.38
    侪
    0.38
     പഴയ
    0.38
     checkpoint
    0.38
    atience
    0.37
    TOOLS
    0.37
    Activations Density 0.001%

    No Known Activations