Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11077
    Prev
    Next
    INDEX
    Explanations

    controversial topics and specific questions

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

    high‑frequency function and light verbs—auxiliaries, modals, and infinitive markers—that express general actions or capability within a sentence.

    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
     dann
    0.40
     डिस्क्रिप्शन
    0.40
    .\"
    0.39
     방법
    0.38
     제가
    0.38
     tohoto
    0.38
     방법을
    0.37
     tych
    0.37
    ständig
    0.37
    lineEdit
    0.36
    POSITIVE LOGITS
    COVID
    0.43
     antisemit
    0.41
     sanctions
    0.39
     vaccination
    0.38
     slavery
    0.38
     transgender
    0.38
     antitrust
    0.38
    睡眠
    0.38
     tinnitus
    0.37
    Brexit
    0.37
    Activations Density 0.069%

    No Known Activations