© 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. 252713
    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
    adien
    0.50
    뉴
    0.49
    क्साइड
    0.49
    חד
    0.48
    툼
    0.46
    녜
    0.46
    lash
    0.46
    mortem
    0.45
    רץ
    0.45
    чный
    0.45
    POSITIVE LOGITS
     over
    0.54
     when
    0.54
     for
    0.52
    :
    0.51
     ?
    0.50
     YELLOW
    0.50
     david
    0.47
     buyers
    0.47
     vacation
    0.46
     overly
    0.46
    Activations Density 0.002%

    No Known Activations