© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    `__main__` guard

    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
    ধু
    2.05
    waża
    1.88
     hxg
    1.84
    ыргыз
    1.83
    В
    1.82
    fahrung
    1.77
    앗
    1.76
    tų
    1.76
    Prz
    1.74
    هایی
    1.73
    POSITIVE LOGITS
     pastime
    2.06
    তন
    1.68
    屓
    1.68
     genre
    1.65
     कार्ट
    1.61
    QRST
    1.60
     haunts
    1.59
    জনক
    1.56
    ॅमिली
    1.56
    ित
    1.56
    Activations Density 0.215%

    No Known Activations