© 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. 109493
    Prev
    Next
    INDEX
    Explanations

    speaking about abstract concepts

    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_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
     parochial
    0.39
    Antae
    0.39
     medieval
    0.38
     Primitive
    0.38
     scarcely
    0.38
     Medieval
    0.37
     ಅಪ
    0.37
    廢
    0.37
     ornamental
    0.36
     Modelling
    0.36
    POSITIVE LOGITS
    icure
    0.42
     науш
    0.39
    唱歌
    0.38
    jor
    0.38
    ﺌ
    0.38
     переме
    0.36
    ناع
    0.36
    斦
    0.36
    endoza
    0.36
     கூறு
    0.36
    Activations Density 0.000%

    No Known Activations