© 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. 4181
    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
    珍惜
    0.46
     Veterans
    0.45
     sleek
    0.45
    0.44
     künstler
    0.44
     COVID
    0.43
    龌
    0.43
     Omicron
    0.42
     opus
    0.42
     DATA
    0.42
    POSITIVE LOGITS
    ie
    0.58
    ग
    0.58
    UIAlert
    0.53
    uradaki
    0.52
    ied
    0.51
    LEncoder
    0.51
    excitation
    0.50
    logistic
    0.50
    urk
    0.50
    enumeration
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.