© 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. 31-GEMMASCOPE-2-RES-262K
    7. 14013
    Prev
    Next
    INDEX
    Explanations

    significance and confidence thresholds

    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_31_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
    巴巴
    0.49
    AndPassword
    0.48
    Billing
    0.45
    备
    0.45
    ğrafl
    0.45
     دستی
    0.44
     voraus
    0.43
     لطف
    0.43
    㴬
    0.43
    沧
    0.42
    POSITIVE LOGITS
     threshold
    0.74
     criterion
    0.65
     thresholds
    0.60
     results
    0.56
     significance
    0.55
    threshold
    0.55
     findings
    0.54
     spurious
    0.54
     decision
    0.52
     evidence
    0.52
    Activations Density 0.053%

    No Known Activations