© 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. 16-GEMMASCOPE-2-RES-262K
    7. 142185
    Prev
    Next
    INDEX
    Explanations

    years and names

    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
     eaves
    0.53
    д
    0.53
    дзі
    0.53
    beds
    0.51
     doping
    0.50
     obstructions
    0.49
     Eurostile
    0.49
     bidders
    0.49
     tolerances
    0.49
    麼
    0.48
    POSITIVE LOGITS
    Date
    0.57
    Feel
    0.54
    TT
    0.54
    Scop
    0.52
    Churn
    0.51
    Disconnect
    0.51
    Tanggal
    0.51
    Re
    0.50
    Hö
    0.50
    DS
    0.50
    Activations Density 0.000%

    No Known Activations