© 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. 260252
    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
    vā
    0.49
    ze
    0.47
     기준으로
    0.47
    ūra
    0.45
    า
    0.45
     위하여
    0.44
     در
    0.44
    se
    0.43
    authorization
    0.43
    nti
    0.43
    POSITIVE LOGITS
     Gérard
    0.49
     sır
    0.45
     motives
    0.44
     Bist
    0.43
     Kut
    0.42
     sucedido
    0.41
    成果
    0.40
    糁
    0.39
     Cajun
    0.39
     sphinx
    0.39
    Activations Density 0.001%

    No Known Activations