© 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. 260483
    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
    TRAILING
    0.56
    تباين
    0.46
    راضي
    0.46
    kbeta
    0.45
    établir
    0.44
    ਛ
    0.44
    ーズ
    0.44
    似
    0.44
    ዙ
    0.43
    binary
    0.43
    POSITIVE LOGITS
     Ats
    0.52
    ("__
    0.52
     Bless
    0.51
     ขอ
    0.50
     Java
    0.50
     รอ
    0.49
     societ
    0.48
     Dynamite
    0.48
     __
    0.47
    .”
    0.47
    Activations Density 0.001%

    No Known Activations