© 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. 253283
    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
     מער
    0.49
     jokingly
    0.48
    𒐪
    0.46
     cashier
    0.45
     digital
    0.45
     conical
    0.45
     renowned
    0.44
     utilisé
    0.44
     traumatic
    0.43
     możesz
    0.42
    POSITIVE LOGITS
    imod
    0.49
    τι
    0.49
    ᱡ
    0.49
    дравствуйте
    0.48
    ار
    0.47
    त्वा
    0.47
    أن
    0.47
    कुछ
    0.45
    Leaves
    0.44
     Vendors
    0.44
    Activations Density 0.000%

    No Known Activations