© 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. 191529
    Prev
    Next
    INDEX
    Explanations

    ®. treats, 5, Figs, Road, œ, betatron

    np_acts-logits-general · gemini-2.5-flash-lite

    technical jargon or names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    studentRecord
    0.40
    ږي
    0.39
    ]++;
    0.38
    浪漫
    0.37
    なのに
    0.36
    ]<<"
    0.36
    claration
    0.35
    adore
    0.35
     म्यू
    0.35
    ";//
    0.35
    POSITIVE LOGITS
     Kreis
    0.40
     physi
    0.39
     Henning
    0.38
     Chu
    0.38
     Martins
    0.38
     dif
    0.38
     genus
    0.37
     Moran
    0.37
     Kahn
    0.37
     Besch
    0.37
    Activations Density 0.005%

    No Known Activations