© 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. 253047
    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
    猢
    0.55
    বাজারে
    0.51
    ﹍
    0.50
    ล้ว
    0.48
    राजनी
    0.48
    iotsitewise
    0.46
    ছোট
    0.46
     साधन
    0.46
     फटाफट
    0.46
    恬
    0.46
    POSITIVE LOGITS
    ↵
    0.64
    OVE
    0.55
    O
    0.46
    ↵↵
    0.46
     Biel
    0.45
    G
    0.44
     fiducia
    0.43
     recruitment
    0.43
     victoria
    0.42
    s
    0.42
    Activations Density 0.000%

    No Known Activations