© 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. 84595
    Prev
    Next
    INDEX
    Explanations

    closed, isolated, enclosed environments

    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
    踐
    0.42
    겸
    0.40
    anzia
    0.39
    ാര
    0.39
     겸
    0.38
     **
    0.38
    razil
    0.38
     ፋ
    0.37
     align
    0.37
     heart
    0.36
    POSITIVE LOGITS
     isolated
    1.73
     изоли
    1.69
    Isolated
    1.63
     Isolated
    1.62
    isolated
    1.60
     closed
    1.56
    封闭
    1.52
     enclosed
    1.50
    Closed
    1.45
     Closed
    1.45
    Activations Density 0.112%

    No Known Activations