© 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. 1052
    Prev
    Next
    INDEX
    Explanations

    counterpart or corresponding element

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

    assignments and parameters

    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
    性和
    0.45
    ❻
    0.41
    驃
    0.40
    なかった
    0.40
    кі
    0.39
    剡
    0.39
    טורק
    0.39
    猢
    0.39
    Scottish
    0.39
    чному
    0.39
    POSITIVE LOGITS
     counterpart
    0.69
     equally
    0.65
     similarly
    0.48
     counterparts
    0.45
     hingegen
    0.43
    ↵↵
    0.43
      
    0.43
    `
    0.42
     correspondingly
    0.41
    *
    0.41
    Activations Density 0.089%

    No Known Activations