© 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. 252840
    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
    a
    0.74
     '
    0.60
     \
    0.58
     S
    0.58
     Package
    0.58
    d
    0.57
    ->
    0.56
     D
    0.55
     Code
    0.54
     $
    0.53
    POSITIVE LOGITS
     έγινε
    0.56
     fizeram
    0.55
     penetrated
    0.53
     günstig
    0.51
     ficaram
    0.50
     intimidated
    0.49
    ફો
    0.49
     gratuitamente
    0.49
     patitth
    0.49
     moest
    0.47
    Activations Density 0.001%

    No Known Activations