© 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. 88847
    Prev
    Next
    INDEX
    Explanations

    Man is, spins into, sent me, has asked, experience to, flour to, shows complete, supply module, needs systems, reporting demos

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

    different perspectives

    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
    牍
    0.48
     ทุก
    0.46
    ında
    0.46
    🪙
    0.46
    缛
    0.46
     乳
    0.46
    งิน
    0.45
    🏧
    0.45
    Ԁ
    0.45
     부동산
    0.45
    POSITIVE LOGITS
     perspectives
    0.48
     agir
    0.47
     focuses
    0.46
     bookshelf
    0.43
     philosophers
    0.43
     econometric
    0.42
     applications
    0.42
     officials
    0.42
     perspectivas
    0.42
     zainteres
    0.42
    Activations Density 0.000%

    No Known Activations