© 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. 13618
    Prev
    Next
    INDEX
    Explanations

    polite offers and requests

    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
    逓
    0.41
     (=
    0.40
     ridicule
    0.39
     stos
    0.39
    痛
    0.39
     ಅನೇಕ
    0.38
    فرج
    0.38
     معنات
    0.37
     demasi
    0.37
    洩
    0.37
    POSITIVE LOGITS
     humbly
    0.67
    提交
    0.64
     willing
    0.61
     pledge
    0.61
     submitted
    0.59
     Pledge
    0.59
     eager
    0.58
     предложить
    0.58
     submission
    0.57
     obedient
    0.57
    Activations Density 0.138%

    No Known Activations