© 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. 17478
    Prev
    Next
    INDEX
    Explanations

    courageous, daring, bold actions

    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
    严
    0.44
    嚴
    0.42
    у
    0.40
     Strugg
    0.40
     stressed
    0.39
     Stru
    0.39
     Stress
    0.39
    stressed
    0.38
    厳
    0.38
    strict
    0.38
    POSITIVE LOGITS
     boldly
    1.59
     bold
    1.55
     audacious
    1.38
     daring
    1.37
     boldness
    1.35
     fearless
    1.27
     bolder
    1.27
     courageous
    1.26
     Bold
    1.23
    Bold
    1.17
    Activations Density 0.008%

    No Known Activations