© 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. 257139
    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
    Linea
    0.47
     estremamente
    0.47
    olutely
    0.46
    িবাস
    0.45
     л
    0.45
     effetto
    0.45
     industria
    0.44
    赫
    0.44
     хлоп
    0.44
     ל
    0.44
    POSITIVE LOGITS
     receiver
    0.46
     Felic
    0.42
     Medici
    0.42
    anam
    0.41
    portion
    0.41
    sr
    0.41
    brauch
    0.41
     zeml
    0.41
     Upan
    0.41
    ਨੇ
    0.41
    Activations Density 0.003%

    No Known Activations