© 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. 253790
    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
    ານ
    0.53
     hates
    0.49
     нико
    0.47
     déb
    0.47
    ައް
    0.47
    珊
    0.46
     націона
    0.46
     extremamente
    0.45
     articulating
    0.45
     канали
    0.45
    POSITIVE LOGITS
    2
    0.71
    4
    0.64
    7
    0.54
    ine
    0.54
    5
    0.53
    Criteria
    0.52
    Pre
    0.51
    3
    0.51
    Event
    0.50
    關於
    0.48
    Activations Density 0.000%

    No Known Activations