© 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. 254508
    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
    vora
    0.54
    t
    0.47
    ذب
    0.47
     Уже
    0.45
    ter
    0.45
     accurate
    0.45
    traffic
    0.44
     Accurate
    0.44
    N
    0.44
    tickets
    0.44
    POSITIVE LOGITS
    დას
    0.48
     менять
    0.46
     BlueprintName
    0.46
     صعبه
    0.46
     разнови
    0.45
     капу
    0.45
     преж
    0.45
     зни
    0.44
     аутох
    0.44
     работают
    0.44
    Activations Density 0.003%

    No Known Activations