© 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. 255881
    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
    Lyric
    0.50
    Lyrics
    0.48
     Lyric
    0.46
     Pflanzen
    0.45
    첸
    0.45
     Lyrics
    0.43
    Kur
    0.43
     Vak
    0.43
     Mostrar
    0.41
    🎹
    0.41
    POSITIVE LOGITS
     sadde
    0.53
    inį
    0.52
    ported
    0.52
     tif
    0.51
    inued
    0.50
    inins
    0.49
     gout
    0.49
     porter
    0.48
     inauguration
    0.48
     corrections
    0.48
    Activations Density 0.000%

    No Known Activations