© 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. 1739
    Prev
    Next
    INDEX
    Explanations

    negative or serious consequences

    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
     LGB
    1.29
    ר
    1.22
     Wien
    1.20
     DON
    1.19
     S
    1.18
     C
    1.16
     Lo
    1.16
     G
    1.16
     R
    1.14
     T
    1.14
    POSITIVE LOGITS
    赚
    1.53
    çay
    1.50
    parin
    1.48
    怀孕
    1.46
     الطيب
    1.45
     dajj
    1.45
    这也
    1.43
     religieux
    1.43
     sağlıklı
    1.43
    quả
    1.42
    Activations Density 0.000%

    No Known Activations