© 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. 28470
    Prev
    Next
    INDEX
    Explanations

    model providing solutions

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

    The neuron strongly activates on the token "model" (i.e., occurrences of the word "model" in system/metadata lines).

    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
     pięk
    0.42
     bellezza
    0.42
    तिहासिक
    0.41
    ल्फी
    0.41
    RationalValue
    0.41
    🦅
    0.40
     reckoning
    0.40
     ዘ
    0.39
     भीषण
    0.38
    ल्पनिक
    0.38
    POSITIVE LOGITS
     SOLUTION
    0.46
     Solution
    0.42
    ు
    0.42
    Solutions
    0.41
    Solution
    0.40
     질문
    0.39
     सहायता
    0.39
     పరిష్
    0.38
    觟
    0.38
    你需要
    0.38
    Activations Density 0.250%

    No Known Activations