© 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. 2041
    Prev
    Next
    INDEX
    Explanations

    frequently, upfront, anymore

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects emphasized/important informational statements in the model's replies—especially headings, strong assertions, and direct advice or explanatory claims.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    К
    0.48
    Data
    0.47
    포
    0.46
    PLIC
    0.46
    IN
    0.43
    МА
    0.42
     initial
    0.42
    РА
    0.42
    Я
    0.42
    ОВА
    0.41
    POSITIVE LOGITS
     pratiquer
    0.45
     situaciones
    0.44
     cenderung
    0.43
     frecuentes
    0.43
     kebanyakan
    0.43
     evita
    0.42
     niektó
    0.41
    習慣
    0.41
     hábitos
    0.40
     regula
    0.40
    Activations Density 0.124%

    No Known Activations