© 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. 175160
    Prev
    Next
    INDEX
    Explanations

    lists and categories

    np_acts-logits-general · gemini-2.5-flash-lite

    punctuation and structural elements

    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
    使其
    0.53
    繩
    0.51
    䒾
    0.48
    
    0.47
    stairs
    0.46
    روج
    0.46
    倉
    0.46
     চো
    0.45
    萆
    0.45
    希望能
    0.44
    POSITIVE LOGITS
     census
    0.50
     kolom
    0.49
     genuine
    0.49
     foundational
    0.48
     serde
    0.48
     thicker
    0.47
     deliber
    0.47
     Symposium
    0.47
     atlas
    0.45
     joystick
    0.45
    Activations Density 0.000%

    No Known Activations