© 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. 83082
    Prev
    Next
    INDEX
    Explanations

    magnetic sticks

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

    following model

    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
    มัน
    0.49
    to
    0.48
    s
    0.48
    PC
    0.47
    )
    0.46
     to
    0.46
    特典
    0.44
     )
    0.43
    ן
    0.42
    Christmas
    0.42
    POSITIVE LOGITS
     තර
    0.53
     scaleOf
    0.52
     အရ
    0.50
     ತುಂಬಾ
    0.47
     শিক্ষার্থীর
    0.47
     inheriting
    0.47
     ಗ್ರ
    0.47
     enigmatic
    0.46
    亿元
    0.45
     ಒಳಗ
    0.45
    Activations Density 0.000%

    No Known Activations