© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4508
    Prev
    Next
    INDEX
    Explanations

    python imports for ml

    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
    Not in Any Lists

    No Comments

    Negative Logits
    trek
    0.45
     trek
    0.41
     Trek
    0.41
     בז
    0.40
    Ა
    0.40
     yī
    0.40
    ိုလ်
    0.40
    elseif
    0.38
    Watercolor
    0.38
    豈
    0.38
    POSITIVE LOGITS
     Trainer
    0.43
     Kass
    0.42
     model
    0.41
     CAS
    0.41
    ann
    0.40
     comment
    0.40
     Bloom
    0.39
     CL
    0.38
    model
    0.37
     Kas
    0.37
    Activations Density 0.002%

    No Known Activations