© 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. 255845
    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
    す
    0.47
    ગર
    0.47
    facebook
    0.46
    image
    0.43
    イメージ
    0.43
    ပါ
    0.43
    ங்கா
    0.42
     bentuk
    0.42
    stato
    0.42
    德
    0.42
    POSITIVE LOGITS
     erhält
    0.49
    निवास
    0.48
    oyle
    0.48
     ይሰ
    0.45
    !".
    0.43
    សម្រាប់ការ
    0.43
    !”.
    0.42
    äus
    0.42
     onsite
    0.41
    ommen
    0.41
    Activations Density 0.001%

    No Known Activations