© 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. 259302
    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
    したがって
    0.48
    Დ
    0.47
     aclar
    0.45
     及
    0.44
    龱
    0.43
    сал
    0.43
     clarifies
    0.43
    ョ
    0.42
    Disposition
    0.42
    Hoist
    0.42
    POSITIVE LOGITS
     date
    0.47
    iego
    0.46
     charitable
    0.43
     charity
    0.42
     to
    0.42
     unavailable
    0.41
    chées
    0.41
     अहि
    0.40
    écie
    0.40
     water
    0.40
    Activations Density 0.000%

    No Known Activations