© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2177
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     in
    0.30
     of
    0.28
     anderen
    0.27
     andre
    0.26
    ↵
    0.26
     Aiden
    0.25
     andere
    0.25
     weitere
    0.25
     andra
    0.24
     Company
    0.24
    POSITIVE LOGITS
     настолько
    0.29
     дуже
    0.25
    不仅
    0.25
     только
    0.24
     не
    0.24
    지가
    0.23
     تنها
    0.23
    ርሃ
    0.22
    ﾚ
    0.22
    only
    0.21
    Activations Density 0.305%

    No Known Activations