© 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. 239505
    Prev
    Next
    INDEX
    Explanations

    ® GAS

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    瞋
    0.50
    😡
    0.49
    ulları
    0.49
    esistenza
    0.46
    艺
    0.46
    驩
    0.46
     अक्सर
    0.46
    ẩu
    0.45
     संजीव
    0.45
    😠
    0.44
    POSITIVE LOGITS
     yoke
    0.53
     kernels
    0.52
     cores
    0.52
     softened
    0.51
     soft
    0.50
     models
    0.49
     regular
    0.49
     modes
    0.48
     sofas
    0.48
     materials
    0.48
    Activations Density 0.002%

    No Known Activations