© 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. 255109
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    c
    0.54
    ut
    0.50
    angulo
    0.46
    uj
    0.44
    Input
    0.43
    pi
    0.43
    pand
    0.43
    ic
    0.43
    uppe
    0.43
    ImageData
    0.43
    POSITIVE LOGITS
    ပေါ
    0.49
    கொ
    0.48
    रोज
    0.47
    ઊ
    0.46
     ezek
    0.46
    шуу
    0.45
     sakin
    0.45
     aki
    0.45
     തുടങ്ങിയ
    0.45
    ຜະລິດຕະພັນ
    0.45
    Activations Density 0.000%

    No Known Activations