© 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. 34403
    Prev
    Next
    INDEX
    Explanations

    produced negative

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

    programming language constructs

    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
     применения
    0.47
     murmured
    0.44
     NIH
    0.43
    樸
    0.43
    ೦
    0.43
     Supernatural
    0.40
    ០
    0.40
    ごろ
    0.39
    მო
    0.39
    )}+
    0.39
    POSITIVE LOGITS
    始终
    0.48
     stall
    0.46
    一方面
    0.45
     nevy
    0.45
     denture
    0.43
     cộng
    0.42
    שט
    0.41
    Rect
    0.41
    を示
    0.41
     khe
    0.41
    Activations Density 0.000%

    No Known Activations