© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4447
    Prev
    Next
    INDEX
    Explanations

    resolving agreements and obligations

    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_13_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
     secondaire
    2.41
     semelhantes
    2.33
     similares
    2.33
     adicionales
    2.32
     descarg
    2.26
    伨
    2.22
     molécules
    2.22
     secondaires
    2.17
     supplémentaires
    2.16
     similaire
    2.14
    POSITIVE LOGITS
     안녕하세요
    1.61
    uesday
    1.59
    지컬
    1.48
    υσ
    1.45
     E
    1.44
    s
    1.44
     지나
    1.43
    펙
    1.42
    OMAS
    1.38
     경우에는
    1.38
    Activations Density 0.008%

    No Known Activations