© 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. 253523
    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
    ALD
    0.51
    ERY
    0.49
    SAR
    0.49
    ЕН
    0.48
    ELE
    0.48
    блю
    0.47
    aln
    0.47
    ᅨ
    0.47
    ্রী
    0.46
    \">\
    0.46
    POSITIVE LOGITS
    Det
    0.82
    det
    0.80
     Det
    0.79
     дете
    0.75
     डिट
    0.74
     डिटे
    0.73
     DET
    0.71
    dets
    0.70
    DET
    0.66
     detik
    0.63
    Activations Density 0.046%

    No Known Activations