© 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. 253709
    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
     પડશે
    0.51
    မှုကို
    0.50
    താ
    0.49
    군의
    0.46
    ৬
    0.45
    ক্রমে
    0.45
    음을
    0.44
    ROUTES
    0.44
    转化为
    0.44
    곱
    0.44
    POSITIVE LOGITS
    he
    0.58
    ais
    0.54
    hes
    0.51
     blanc
    0.50
     liberal
    0.49
    rahmen
    0.49
    holder
    0.48
     elephant
    0.47
     mies
    0.47
    hors
    0.46
    Activations Density 0.001%

    No Known Activations