© 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. 254257
    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
    ंचा
    0.49
    捲
    0.49
    ባድ
    0.46
     dérou
    0.45
    ۆی
    0.45
    んだけど
    0.45
     কিছু
    0.43
    ंधी
    0.42
    んですけど
    0.41
     configurational
    0.41
    POSITIVE LOGITS
    h
    0.64
    fd
    0.51
    ra
    0.50
    há
    0.50
    hare
    0.50
    translations
    0.49
    hara
    0.49
    hak
    0.49
    hana
    0.49
    hz
    0.48
    Activations Density 0.001%

    No Known Activations