© 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. 7395
    Prev
    Next
    INDEX
    Explanations

    from ... import

    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
     sekar
    0.93
    埋
    0.87
     sebagai
    0.84
    擁
    0.80
     roli
    0.79
     kritis
    0.79
    当我
    0.79
     vei
    0.78
     enfrent
    0.77
    봉
    0.77
    POSITIVE LOGITS
     standpoint
    1.17
     Perspective
    1.15
     ጋር
    1.12
    ዐ
    1.10
     በላይ
    1.08
     שב
    1.08
     পরিত্র
    1.07
     Из
    1.06
    perspective
    1.06
     perspective
    1.06
    Activations Density 0.172%

    No Known Activations