© 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. 64586
    Prev
    Next
    INDEX
    Explanations

    section introductions and examples

    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
     Support
    0.47
     paru
    0.46
    kin
    0.45
     Audience
    0.44
    ғы
    0.44
     Jan
    0.43
    ,
    0.43
    -
    0.43
    am
    0.43
     averages
    0.43
    POSITIVE LOGITS
    Pale
    0.52
     frescoes
    0.50
     viciss
    0.48
     teint
    0.47
    Limite
    0.47
    Memento
    0.47
    ುತ್ತವೆ
    0.47
     cataracts
    0.47
     caldera
    0.46
    RESOL
    0.46
    Activations Density 0.003%

    No Known Activations