© 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. 13524
    Prev
    Next
    INDEX
    Explanations

    therapist, software development, myth

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

    This neuron fires strongly on tokens that are numeric or technical identifiers (long digit sequences, hashes, numeric codes, and similar inline code/command tokens).

    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
     Saleem
    0.45
     دوسرا
    0.42
    GIL
    0.41
     வெள்ளை
    0.40
    ത്തിലുള്ള
    0.39
    '_
    0.39
    മായിരുന്നു
    0.38
     Exports
    0.38
     داش
    0.38
     दूसरा
    0.38
    POSITIVE LOGITS
    рно
    0.48
    纾
    0.46
    ीट
    0.45
     kebanyakan
    0.44
     Zones
    0.44
     Bonifacio
    0.43
     byt
    0.42
    alista
    0.41
    nogo
    0.40
    கம்
    0.38
    Activations Density 4.340%

    No Known Activations