© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 14108
    Prev
    Next
    INDEX
    Explanations

    courage and signs of strength

    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_65k_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
     wygl
    0.44
     expects
    0.43
    즐
    0.42
     enjoying
    0.42
    Expect
    0.41
     wants
    0.40
     expect
    0.39
     즐
    0.39
     Bells
    0.39
     enjoys
    0.38
    POSITIVE LOGITS
     courage
    0.97
     bravery
    0.96
     courageous
    0.95
     commendable
    0.90
     bravely
    0.81
     सराह
    0.81
     valiant
    0.81
    勇气
    0.78
     brave
    0.76
     admirable
    0.76
    Activations Density 0.153%

    No Known Activations