© 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. 253566
    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
    다면
    0.59
    溇
    0.54
    다는
    0.53
    岁
    0.53
     Drafting
    0.53
    书中
    0.52
    郓
    0.52
    舰队
    0.51
    铁路
    0.50
    🛣
    0.50
    POSITIVE LOGITS
     zucchero
    0.58
    is
    0.55
     activ
    0.55
     amplitudes
    0.55
     analyses
    0.55
     funziona
    0.55
     proteínas
    0.54
     caffeine
    0.54
     neurop
    0.53
     destabil
    0.53
    Activations Density 0.000%

    No Known Activations