© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111297
    Prev
    Next
    INDEX
    Explanations

    status, entities, states, or results

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

    The neuron detects key content nouns and technical/quantitative terms (domain-specific entities, measurements, statuses and similar important words).

    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
    <unused683>
    0.34
    𝖆
    0.34
    <unused2006>
    0.33
    𝟰
    0.33
    ícul
    0.32
     Anche
    0.32
    idikan
    0.32
    াইয়৷
    0.31
    𝟭
    0.31
    <unused732>
    0.31
    POSITIVE LOGITS
     increases
    0.33
     last
    0.32
     index
    0.32
     inflate
    0.32
     bu
    0.29
     validity
    0.29
     he
    0.29
     ends
    0.28
    ጩ
    0.28
     bit
    0.28
    Activations Density 0.400%

    No Known Activations