© 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. 10067
    Prev
    Next
    INDEX
    Explanations

    checking for null

    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
    nergy
    2.17
    <bos>
    2.01
    垦
    1.99
    nev
    1.98
    relatively
    1.96
    nal
    1.92
    rets
    1.91
    ruz
    1.89
    ্ম্ম
    1.89
    YK
    1.86
    POSITIVE LOGITS
    ি
    2.97
    tuk
    2.68
    ture
    2.68
    tin
    2.63
    t
    2.61
    tat
    2.49
    tir
    2.30
    ੀ
    2.30
    tie
    2.26
    ಜಿ
    2.24
    Activations Density 0.001%

    No Known Activations