© 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. 260692
    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
    adir
    0.45
     blok
    0.45
    à
    0.44
     филь
    0.42
     verkaufen
    0.42
     serão
    0.42
     befinden
    0.42
    濾
    0.42
    ảy
    0.42
    ścic
    0.41
    POSITIVE LOGITS
     wisely
    0.49
     attained
    0.45
     silver
    0.45
     MAST
    0.45
     afar
    0.45
    STE
    0.43
    峽
    0.43
     जाते
    0.43
     few
    0.43
     above
    0.42
    Activations Density 0.000%

    No Known Activations