© 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. 84431
    Prev
    Next
    INDEX
    Explanations

    inference using, evolutionary adaptation, sounds nice

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

    The neuron detects text about performing model inference or instructions for running inference (discussions of carrying out inference).

    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
    這邊
    0.47
     എന്നാല്‍
    0.45
    ение
    0.44
     כבר
    0.43
    ╧
    0.42
    shovel
    0.41
    getFullName
    0.41
    CodeableConcept
    0.41
    CTOGRAM
    0.41
    那时候
    0.41
    POSITIVE LOGITS
     attacking
    0.47
     using
    0.45
     bee
    0.45
     mars
    0.45
     rectify
    0.44
     c
    0.43
     cross
    0.43
     man
    0.43
     stay
    0.42
     C
    0.41
    Activations Density 0.000%

    No Known Activations