© 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. 6962
    Prev
    Next
    INDEX
    Explanations

    iterating with enumerate

    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
    e
    2.98
    ी
    2.96
    tus
    2.76
    ি
    2.70
    ので
    2.51
    pth
    2.50
    g
    2.48
    té
    2.43
    dai
    2.43
    t
    2.42
    POSITIVE LOGITS
    omial
    2.30
    었
    2.28
    APOLIS
    2.27
    rolled
    2.14
    coln
    2.06
    ahme
    2.05
    ্ধ্য
    2.05
    ্ড
    2.03
    বীন্দ্র
    2.02
    ning
    1.99
    Activations Density 0.352%

    No Known Activations