© 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-65K
    7. 27672
    Prev
    Next
    INDEX
    Explanations

    acceptance or limits

    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_65k_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
    㖩
    0.46
    énieur
    0.42
     από
    0.41
    ädchen
    0.41
     चलन
    0.40
    ImageIcon
    0.40
     způ
    0.40
     Zool
    0.40
     Tử
    0.40
    舰
    0.40
    POSITIVE LOGITS
     barn
    0.42
     curated
    0.41
     decisiones
    0.40
    вай
    0.40
     kev
    0.39
    жного
    0.39
    และการ
    0.39
     vart
    0.39
    michael
    0.38
     нама
    0.38
    Activations Density 0.001%

    No Known Activations