© 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. 123349
    Prev
    Next
    INDEX
    Explanations

    phrases connecting modifiers and their subjects

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

    requirements, number of gifts

    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
     hapless
    0.48
     doctrina
    0.46
     اصول
    0.46
     megal
    0.46
     عہد
    0.45
     독
    0.45
     postwar
    0.45
     stern
    0.45
     mundial
    0.44
     nonchal
    0.44
    POSITIVE LOGITS
    と呼ばれる
    0.47
    กิน
    0.47
    เหล่านี้
    0.46
    寄せ
    0.44
    ственным
    0.44
    ซื้อ
    0.43
    ppi
    0.43
    蔬
    0.42
    食物
    0.42
    的其他
    0.42
    Activations Density 0.000%

    No Known Activations