© 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. 15811
    Prev
    Next
    INDEX
    Explanations

    on followed by method 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_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
     compressible
    0.47
    gdock
    0.45
     कंप्र
    0.45
    linestyle
    0.43
    ᓕ
    0.42
    頜
    0.42
    ValueLayout
    0.42
    لین
    0.42
    褻
    0.42
    लाइन
    0.41
    POSITIVE LOGITS
     Bind
    0.58
    Bind
    0.57
     Binding
    0.54
    bind
    0.52
     bind
    0.52
     onView
    0.52
     binds
    0.50
     binding
    0.49
     on
    0.46
    glBind
    0.46
    Activations Density 0.001%

    No Known Activations