© 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. 100946
    Prev
    Next
    INDEX
    Explanations

    non-english script characters

    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
     aluminum
    0.45
    .[/
    0.43
     magnis
    0.43
    ;,
    0.42
     Hemat
    0.40
    assembl
    0.40
    *,
    0.40
     Metall
    0.39
    ൂരി
    0.39
     thereby
    0.39
    POSITIVE LOGITS
     λε
    0.44
    ן
    0.44
     состояние
    0.43
    ਏ
    0.43
    線
    0.43
     ของ
    0.42
    ંગી
    0.42
    逮
    0.42
    ⵚ
    0.42
     связь
    0.41
    Activations Density 0.014%

    No Known Activations