© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55424
    Prev
    Next
    INDEX
    Explanations

    a specific list item

    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
    рті
    0.46
     sandwiched
    0.43
     області
    0.43
    ğinin
    0.42
    掍
    0.42
     vergang
    0.41
     мелдеш
    0.41
     questões
    0.41
     slumped
    0.41
    шенный
    0.41
    POSITIVE LOGITS
    t
    0.74
    node
    0.56
    1
    0.56
    any
    0.50
    g
    0.50
    ope
    0.50
    arc
    0.49
    way
    0.49
    tp
    0.48
    nn
    0.48
    Activations Density 0.008%

    No Known Activations