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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11000
    Prev
    Next
    INDEX
    Explanations

    not found or does not exist

    np_acts-logits-general · gemini-2.5-flash-lite

    file not found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    버
    0.41
    Женско
    0.40
     bursting
    0.40
    暖かい
    0.39
    瑾
    0.38
    burst
    0.38
     Linie
    0.38
     Burst
    0.37
    ሥ
    0.37
     FLASH
    0.37
    POSITIVE LOGITS
    NotFound
    1.83
    notFound
    1.70
     NotFound
    1.62
    找不到
    1.54
    不存在
    1.48
     inexist
    1.48
     nonexistent
    1.35
    NotExist
    1.33
    NotFoundError
    1.20
    DoesNotExist
    1.14
    Activations Density 0.074%

    No Known Activations