© 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. 195497
    Prev
    Next
    INDEX
    Explanations

    code, math, and technical terms

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

    This neuron responds strongly to apostrophes/quote characters (tokens used in contractions or possessives).

    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
     handouts
    0.46
    ABILITIES
    0.44
    権
    0.40
    ปรับ
    0.40
     callbacks
    0.38
     Brownian
    0.38
     easements
    0.38
    ｒ
    0.38
     calamities
    0.37
     CALLBACK
    0.37
    POSITIVE LOGITS
     Tan
    0.39
     Tom
    0.38
    engen
    0.38
    澄清
    0.37
     svare
    0.37
     savo
    0.35
     Embar
    0.35
    Tom
    0.35
     conjugate
    0.35
    Sunday
    0.35
    Activations Density 0.013%

    No Known Activations