© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    periods and quotes

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

    sentences or phrases written in a strongly voiced first‑person (I) perspective expressing emotion—often humorous, sarcastic, or emphatic commentary.

    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
     مقام
    0.30
    瑙
    0.29
     되면
    0.27
     земель
    0.27
    깽
    0.27
    Repartition
    0.25
    에서의
    0.25
    MOVEMENT
    0.25
    ेंशियल
    0.25
    撩
    0.24
    POSITIVE LOGITS
     দেখলাম
    0.41
    6
    0.35
    bt
    0.34
     পারিনি
    0.33
     मैंने
    0.32
     Same
    0.32
     nisam
    0.32
    9
    0.32
    0
    0.31
     оказалось
    0.31
    Activations Density 0.039%

    No Known Activations