© 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. 259822
    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
    תו
    0.52
    ಟ
    0.51
    AKE
    0.49
    มาะ
    0.47
    ET
    0.47
    AIN
    0.47
    ;*/
    0.46
    تا
    0.45
    เหมาะ
    0.45
    ิ
    0.45
    POSITIVE LOGITS
     operação
    0.49
     operación
    0.49
     Specifies
    0.45
     flaky
    0.45
     która
    0.44
     appreciates
    0.43
     Ereign
    0.43
     piezoelectric
    0.43
     której
    0.42
     peças
    0.42
    Activations Density 0.002%

    No Known Activations