© 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. 256179
    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
    ([])
    0.50
    perp
    0.48
     hém
    0.48
    dx
    0.46
    惘
    0.46
    bys
    0.46
    枳
    0.46
     вза
    0.46
    ons
    0.45
    Emily
    0.45
    POSITIVE LOGITS
     astronomical
    0.54
     ballistic
    0.52
    ಿತ
    0.47
    торов
    0.46
     $
    0.46
     ellipsoid
    0.45
     Quadrup
    0.44
     batsmen
    0.44
     seasonal
    0.44
     snowfall
    0.43
    Activations Density 0.000%

    No Known Activations