© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113165
    Prev
    Next
    INDEX
    Explanations

    a sprite, a Medieval

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

    how x relate to y

    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
    6
    0.48
    guy
    0.46
    таж
    0.46
     tiem
    0.46
    credibly
    0.46
    찌
    0.45
    점에
    0.45
    al
    0.45
    avail
    0.45
    兄
    0.44
    POSITIVE LOGITS
    Kemudian
    0.48
     sécrétion
    0.48
     refuted
    0.47
     resuspended
    0.47
     belül
    0.46
     pédicule
    0.46
     اتباع
    0.46
     zásobníku
    0.46
     kammam
    0.45
     পলিপ
    0.45
    Activations Density 0.000%

    No Known Activations