© 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. 62061
    Prev
    Next
    INDEX
    Explanations

    visual elements and relations

    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
    ାଇ
    0.54
    ясплат
    0.50
     родители
    0.50
    ჷ
    0.49
     maatau
    0.47
    できない
    0.47
    🐲
    0.46
    Lorsque
    0.45
     pyaar
    0.45
     شرطونو
    0.45
    POSITIVE LOGITS
     whitish
    0.48
     shading
    0.46
     bluish
    0.46
     canvas
    0.44
     화면
    0.44
     shadowy
    0.44
     hues
    0.44
     tint
    0.43
    "
    0.42
     filamentous
    0.42
    Activations Density 0.027%

    No Known Activations