© 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. 3364
    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
    Ბ
    0.58
    委员
    0.57
    갔
    0.56
    权力
    0.54
    产权
    0.52
    客观
    0.52
    广大
    0.52
    allenges
    0.52
    读者
    0.52
    精致
    0.52
    POSITIVE LOGITS
    0.67
    én
    0.58
    u
    0.56
     m
    0.56
     moje
    0.55
     c
    0.55
    ên
    0.55
    iz
    0.54
    du
    0.54
     du
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.