© 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. 257088
    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
    });
    0.46
     shameful
    0.45
    ზ
    0.43
    ನೀ
    0.42
    ".
    0.41
     dissimilar
    0.41
    ->
    0.41
     fiscale
    0.40
    pdfs
    0.40
    POSITIVE LOGITS
     പ്രതീ
    0.54
     गर्ने
    0.47
     نیک
    0.47
     Battalion
    0.46
     Coroner
    0.46
    苕
    0.46
    alanx
    0.45
     పాఠ
    0.45
     vš
    0.45
     Precinct
    0.45
    Activations Density 0.001%

    No Known Activations