© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12292
    Prev
    Next
    INDEX
    Explanations

    Microsoft 365

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ed
    3.62
    ball
    3.08
    ડ
    2.85
    r
    2.85
    li
    2.74
    ة
    2.64
    ness
    2.54
    숙
    2.51
    kom
    2.50
    cu
    2.48
    POSITIVE LOGITS
    omitempty
    3.04
     говорить
    2.79
     доход
    2.63
    ݢ
    2.62
    WeakTable
    2.60
    efficients
    2.57
    itung
    2.56
     эффек
    2.55
    OPER
    2.55
    Percentages
    2.55
    Activations Density 0.000%

    No Known Activations