© 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. 253215
    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
     проє
    0.49
     搭
    0.45
     promin
    0.44
     schützen
    0.44
     prominent
    0.44
    Donc
    0.43
    ↵
    0.42
    ನ್
    0.42
    ם
    0.42
    Y
    0.41
    POSITIVE LOGITS
    diği
    0.46
    멱
    0.46
    
    0.45
     মার্শাল
    0.45
     полностью
    0.44
    RelativeLayout
    0.44
     wyłącznie
    0.44
    Verifier
    0.43
    ilesh
    0.43
    änt
    0.43
    Activations Density 0.000%

    No Known Activations