© 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. 46098
    Prev
    Next
    INDEX
    Explanations

    majestic outdoor

    np_acts-logits-general · gemini-2.5-flash-lite

    self-punishment

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     bistro
    0.45
     Bison
    0.45
     Bistro
    0.44
     Mez
    0.42
     deportes
    0.41
     Processor
    0.41
    만
    0.41
    йи
    0.40
     haces
    0.40
     Buffalo
    0.40
    POSITIVE LOGITS
     оттен
    0.50
    Ȧ
    0.47
     einigen
    0.47
     wavelengths
    0.46
    oq
    0.46
    心里
    0.45
     intensities
    0.45
     Matlab
    0.45
    offre
    0.44
     आश्
    0.44
    Activations Density 0.000%

    No Known Activations