© 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. 86754
    Prev
    Next
    INDEX
    Explanations

    scored, unearned

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

    Plugin Name:

    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
    변
    0.52
    ण्ट
    0.47
    preset
    0.46
     liberally
    0.45
     Carnegie
    0.45
    mitted
    0.44
     तत्काल
    0.43
    s
    0.43
     bilo
    0.43
     Ceiling
    0.43
    POSITIVE LOGITS
    你們
    0.52
    晞
    0.48
    工事
    0.48
    рія
    0.48
    看似
    0.47
    戲
    0.47
    的公司
    0.45
    XI
    0.44
     「
    0.43
    亮点
    0.43
    Activations Density 0.002%

    No Known Activations