© 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. 3255
    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
     perform
    0.47
     dü
    0.46
     th
    0.45
    班牙
    0.44
     ditu
    0.44
    Siehe
    0.42
     cheapest
    0.41
    贊
    0.41
     cheap
    0.41
     communicate
    0.41
    POSITIVE LOGITS
    lara
    0.51
    morale
    0.50
    lod
    0.49
    ことから
    0.48
    などが
    0.48
    '])->
    0.48
     rojos
    0.47
     なら
    0.47
    lardan
    0.47
     変
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.