© 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. 255623
    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
    optim
    0.50
    s
    0.50
    msg
    0.49
    allowed
    0.49
    membrane
    0.48
    zn
    0.48
    opened
    0.46
    mat
    0.46
    ak
    0.45
    visible
    0.45
    POSITIVE LOGITS
     ഹ
    0.46
    地區
    0.45
     nõ
    0.45
     submer
    0.44
     馬
    0.44
     จังหวัด
    0.43
     Following
    0.42
     որ
    0.42
    ുവ
    0.42
     châ
    0.42
    Activations Density 0.000%

    No Known Activations