© 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. 259870
    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
    番組
    0.49
    奚
    0.47
    OffsetY
    0.47
    奶奶
    0.45
    辛苦
    0.44
    休暇
    0.44
    睡眠
    0.44
    晤
    0.44
     ಪ್ರಯೋಜನ
    0.43
    とっても
    0.43
    POSITIVE LOGITS
     apparten
    0.47
     heavenly
    0.46
     sharpness
    0.46
     Heavenly
    0.46
     According
    0.45
     Sweep
    0.44
     endian
    0.43
     clarity
    0.43
     entirety
    0.43
     möglicherweise
    0.43
    Activations Density 0.001%

    No Known Activations