© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239709
    Prev
    Next
    INDEX
    Explanations

    official processes

    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
    Gif
    0.49
    OfInterest
    0.46
    Aj
    0.45
    Immediate
    0.45
    Coef
    0.45
    人
    0.45
    爛
    0.44
    SnackBar
    0.44
    Zak
    0.44
    Alarm
    0.43
    POSITIVE LOGITS
     fluctu
    0.47
     impresión
    0.45
     nación
    0.43
    titulo
    0.42
     aumentó
    0.42
     mette
    0.42
     Londra
    0.41
     beeindruck
    0.41
     mediante
    0.41
    ӓ
    0.40
    Activations Density 0.001%

    No Known Activations