© 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. 110545
    Prev
    Next
    INDEX
    Explanations

    descriptions of things

    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
    GBuf
    0.42
     ㄴ
    0.41
    MakeRect
    0.39
    ENSATION
    0.39
     অনুবাদ
    0.38
     syncing
    0.38
     taea
    0.38
     ಅನುಪಾತ
    0.38
     っ
    0.38
    --)
    0.37
    POSITIVE LOGITS
     Pepper
    0.42
     Roses
    0.40
     Entrepreneur
    0.40
    环
    0.39
     Crest
    0.39
     Pelican
    0.39
     Boats
    0.38
     Good
    0.38
    لوث
    0.37
    你们
    0.37
    Activations Density 0.000%

    No Known Activations