© 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. 253785
    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
    走行
    0.45
    Weiss
    0.44
    食用
    0.42
     コス
    0.42
    雑
    0.42
     clockRadius
    0.42
    毖
    0.41
    すみ
    0.40
     антенна
    0.40
     মিলন
    0.39
    POSITIVE LOGITS
     reversion
    0.47
     inverse
    0.46
     revers
    0.45
     Inverse
    0.45
     reversing
    0.44
     recipro
    0.44
    inverse
    0.44
     reclaiming
    0.44
    reversed
    0.43
     inverses
    0.43
    Activations Density 0.007%

    No Known Activations