Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 76776
    Prev
    Next
    INDEX
    Explanations

    argument tells or uses

    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
     Sovereign
    0.49
    өрү
    0.44
    鹑
    0.44
    ру
    0.43
    ương
    0.43
     Weston
    0.43
     flotation
    0.43
     mondial
    0.42
     Sonu
    0.42
     penultimate
    0.42
    POSITIVE LOGITS
    FBI
    0.47
     طراحی
    0.46
    There
    0.45
    Tinh
    0.43
    Design
    0.42
    רג
    0.42
    Encyclopedia
    0.41
    ∋
    0.41
    TH
    0.41
    eqn
    0.41
    Activations Density 0.000%

    No Known Activations