© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2442
    Prev
    Next
    INDEX
    Explanations

    in multiple contexts

    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_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
    ’
    0.33
     (
    0.32
     In
    0.32
    ↵
    0.31
    D
    0.31
     A
    0.30
    In
    0.30
    ↵↵
    0.30
    L
    0.30
    A
    0.29
    POSITIVE LOGITS
     regard
    0.44
     regards
    0.43
     отношении
    0.36
     realms
    0.36
     contexts
    0.35
     contextos
    0.33
     respecto
    0.33
     terms
    0.33
     forbindelse
    0.33
     relation
    0.32
    Activations Density 0.272%

    No Known Activations