© 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. 253065
    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
    ujeme
    0.57
    ují
    0.55
    E
    0.50
     compete
    0.45
    ları
    0.45
    Ahora
    0.45
    wee
    0.45
     Eingang
    0.45
     debut
    0.45
     flamboyant
    0.44
    POSITIVE LOGITS
    getCql
    0.49
     capacitances
    0.48
    աք
    0.47
     theses
    0.47
    𝐷
    0.47
     andDevice
    0.46
     estern
    0.46
     większość
    0.46
    🌥
    0.46
    чній
    0.46
    Activations Density 0.001%

    No Known Activations