© 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. 253945
    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
     ☑
    0.46
     Hour
    0.43
    ৩৮
    0.43
     HOUR
    0.42
     vang
    0.41
     solns
    0.40
     хан
    0.40
     ○
    0.39
    🙏🙏
    0.39
     साधन
    0.39
    POSITIVE LOGITS
    詐
    0.41
    ゃ
    0.40
    прежнему
    0.40
     Michaelmas
    0.39
    쓰
    0.39
     tête
    0.39
    чат
    0.38
    ocentric
    0.38
    ایط
    0.38
    ază
    0.38
    Activations Density 0.007%

    No Known Activations