© 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. 15515
    Prev
    Next
    INDEX
    Explanations

    statistical comparison

    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
     страте
    0.44
     Strateg
    0.43
     strategi
    0.43
    aturamento
    0.43
    焦點
    0.43
     strategia
    0.42
     रणनीति
    0.42
    铛
    0.41
     dàn
    0.40
     strateg
    0.40
    POSITIVE LOGITS
     ceilings
    0.61
     ceiling
    0.60
     repeatable
    0.57
     repeatability
    0.56
    ceiling
    0.55
     Ceiling
    0.54
     developmental
    0.50
     outlier
    0.50
    Regression
    0.49
    Statistical
    0.49
    Activations Density 0.008%

    No Known Activations