© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139305
    Prev
    Next
    INDEX
    Explanations

    a version

    np_acts-logits-general · gemini-2.5-flash-lite

    between myself and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    很是
    0.50
     fes
    0.49
     obstructive
    0.48
    葫
    0.48
     inhoud
    0.47
     envio
    0.47
     çıkar
    0.46
     gider
    0.46
     whol
    0.46
     preocupación
    0.46
    POSITIVE LOGITS
    ETA
    0.50
    setosa
    0.48
    ritu
    0.48
    ≾
    0.47
     midfielders
    0.47
    렵
    0.47
    resnet
    0.46
    etin
    0.46
    strstr
    0.46
    Nil
    0.46
    Activations Density 0.000%

    No Known Activations