© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14072
    Prev
    Next
    INDEX
    Explanations

    Natural Language Processing

    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
    s
    1.69
    sin
    1.64
    sg
    1.63
    sr
    1.61
    sl
    1.58
    sex
    1.57
    س
    1.54
    sing
    1.54
    سوم
    1.51
    𝐬
    1.48
    POSITIVE LOGITS
     რე
    2.06
    rparam
    2.01
     assemblages
    2.01
    Ւ
    2.00
    unprocessable
    2.00
    ونی
    2.00
    នុ
    2.00
     सुरू
    1.98
    此之外
    1.92
    主流
    1.91
    Activations Density 0.019%

    No Known Activations