© 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. 40-GEMMASCOPE-2-RES-262K
    4. 133753
    Prev
    Next
    INDEX
    Explanations

    proportions, security, content

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

    the neuron detects important content words — the meaningful nouns, verbs, and adjectives that carry the main information in a sentence.

    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_40_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
    erapeut
    0.41
    ኾ
    0.39
     dies
    0.39
    ؤال
    0.38
     chars
    0.38
    零售
    0.38
     Danish
    0.38
    Retail
    0.38
     aDAO
    0.38
     ఆల
    0.37
    POSITIVE LOGITS
     மன்ற
    0.36
    rost
    0.34
    uncia
    0.34
     melibatkan
    0.34
     মধ্যে
    0.33
    跄
    0.33
     Provost
    0.33
     Schwerpunkt
    0.33
     wiadomo
    0.33
     চিত্র
    0.33
    Activations Density 0.000%

    No Known Activations