© 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-262K
    7. 205184
    Prev
    Next
    INDEX
    Explanations

    element * is *unique*

    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
    рія
    0.50
     lifting
    0.49
     ressent
    0.49
     diciembre
    0.49
    :
    0.48
     incluso
    0.48
     nombrado
    0.48
     hormone
    0.47
     surtout
    0.47
     Adrienne
    0.47
    POSITIVE LOGITS
    laut
    0.45
    帛
    0.44
    形式
    0.44
     ውሃ
    0.44
    ushes
    0.43
    AKI
    0.42
    的形式
    0.42
    lardır
    0.42
    onik
    0.42
    erun
    0.41
    Activations Density 0.000%

    No Known Activations