© 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. 133491
    Prev
    Next
    INDEX
    Explanations

    titles, symbols, and specific terms

    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
     chapter
    0.41
     Section
    0.41
     function
    0.40
     section
    0.39
     univ
    0.39
     cm
    0.38
     partitioned
    0.38
     B
    0.38
     partition
    0.38
     percentile
    0.38
    POSITIVE LOGITS
    รือ
    0.49
    )،
    0.45
    หรือ
    0.42
     devenu
    0.41
     adı
    0.41
    الص
    0.40
     когда
    0.40
     பெயர்
    0.40
    PopMatrix
    0.40
     титу
    0.39
    Activations Density 0.004%

    No Known Activations