© 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. 145527
    Prev
    Next
    INDEX
    Explanations

    financial or legal entities

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

    land from oceans

    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
    ،
    0.55
    were
    0.53
    、
    0.50
    。
    0.49
    ፣
    0.48
    ؛
    0.47
    are
    0.45
     và
    0.45
     şi
    0.44
     každ
    0.44
    POSITIVE LOGITS
    単純
    0.46
     modifies
    0.46
     ಸುಬ್ಬ
    0.43
    ようです
    0.42
    দীর
    0.42
    ಙ
    0.42
     ভাবের
    0.41
     communicate
    0.41
     broaden
    0.41
     улучшения
    0.41
    Activations Density 0.001%

    No Known Activations