© 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. 202101
    Prev
    Next
    INDEX
    Explanations

    public debt ratio

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

    class definitions and data structures

    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
     createWindow
    0.45
     नमस्ते
    0.43
     hepin
    0.42
     pertemuan
    0.41
     энерго
    0.40
     냉
    0.40
    नमस्ते
    0.39
    痉
    0.39
    ௦
    0.39
     nip
    0.39
    POSITIVE LOGITS
    字段
    0.41
    (":")[
    0.39
    JsonKey
    0.38
    ミラー
    0.38
    呆
    0.38
    omitempty
    0.38
    }?
    0.37
    TimeTo
    0.37
    =:
    0.37
     jsonObj
    0.37
    Activations Density 0.005%

    No Known Activations