© 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-262K
    4. 4313
    Prev
    Next
    INDEX
    Explanations

    how can explain it

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

    the ends of sentences and the starts of questions or instructions, reacting to end punctuation, newline markers, and interrogative/opening prompt cues.

    oai_token-act-pair · gpt-5Triggered 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
     adhesion
    0.43
     intégr
    0.40
     publiés
    0.40
     clockRadius
    0.39
    QRY
    0.39
    皘
    0.39
    ॢ
    0.38
     cranberries
    0.38
    🙏🏻
    0.38
     admixture
    0.37
    POSITIVE LOGITS
     Therefore
    0.73
     Why
    0.70
     However
    0.67
     लेकिन
    0.64
     But
    0.63
     How
    0.63
     ಏಕೆ
    0.63
     Почему
    0.62
     but
    0.58
     इसलिए
    0.58
    Activations Density 0.187%

    No Known Activations