© 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. 255355
    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
     Decorative
    0.47
    Decorative
    0.43
    阳光
    0.42
     Duval
    0.42
    Standard
    0.42
    沃尔
    0.41
    呦
    0.40
    Lear
    0.40
     Scal
    0.40
    Quick
    0.40
    POSITIVE LOGITS
     culprits
    0.50
    गज
    0.47
     mencionado
    0.47
    खो
    0.44
     barbaric
    0.44
    ۶
    0.43
     alluded
    0.43
     monstrous
    0.42
    ಿತ್ತು
    0.42
     cambiato
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.