© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 257927
    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
    attham
    0.49
    idbody
    0.49
    ovanja
    0.48
    ंकन
    0.47
    BOL
    0.47
    Bike
    0.46
    ̣i
    0.46
    )--
    0.46
    kadang
    0.46
    Notifier
    0.46
    POSITIVE LOGITS
     concentration
    0.49
     vanguard
    0.48
     stata
    0.47
     sch
    0.46
     بش
    0.46
     난
    0.46
     nymph
    0.45
    វេល
    0.44
     lacer
    0.44
     bầu
    0.44
    Activations Density 0.000%

    No Known Activations