© 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. 256921
    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
     Públic
    0.48
     বাঙ্গালার
    0.47
     ग्रुप
    0.46
     ROUILLER
    0.45
    峒
    0.44
    耔
    0.44
    }=-
    0.43
    }$;
    0.43
     वित्त
    0.43
     ὑ
    0.43
    POSITIVE LOGITS
    weave
    0.49
    στημα
    0.47
    io
    0.46
    ex
    0.46
    댐
    0.43
    vedad
    0.42
    (&(
    0.42
    eman
    0.42
    JN
    0.41
    VY
    0.41
    Activations Density 0.001%

    No Known Activations