© 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. 255901
    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
    ቫ
    0.49
    ണിക്ക
    0.48
    我们要
    0.48
    我們會
    0.48
    entiti
    0.48
     hjæl
    0.47
     helpline
    0.47
    덬
    0.45
    हमारी
    0.45
    ਟਰ
    0.45
    POSITIVE LOGITS
     Fate
    0.51
     menacing
    0.48
     muttered
    0.47
     climbed
    0.45
     Biochim
    0.44
     Death
    0.43
     grinned
    0.42
     feathered
    0.42
     Celestial
    0.42
     montée
    0.41
    Activations Density 0.000%

    No Known Activations