© 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. 31-GEMMASCOPE-2-RES-262K
    4. 3737
    Prev
    Next
    INDEX
    Explanations

    common verb endings

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

    This neuron detects first- and second-person pronouns and self-/audience-referential tokens (e.g., "I", "we", "you", contractions like "we're"/"I'm").

    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_31_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
     বাধ্যতামূলক
    0.16
    เป็น
    0.16
    1
    0.16
    万
    0.16
    อะไร
    0.16
    %
    0.16
    분
    0.15
     acknowledgment
    0.15
    *
    0.15
    м
    0.15
    POSITIVE LOGITS
     possa
    0.16
     pria
    0.16
     want
    0.15
     tego
    0.15
     questi
    0.15
     tomto
    0.15
     quero
    0.14
    ﻱ
    0.14
     pazienti
    0.14
     pacientes
    0.14
    Activations Density 0.709%

    No Known Activations