© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2944
    Prev
    Next
    INDEX
    Explanations

    In

    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_7_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
    nya
    3.39
    te
    2.95
    了
    2.90
    ss
    2.83
    다는
    2.82
    na
    2.69
    tha
    2.66
    다고
    2.65
    sa
    2.62
    ther
    2.58
    POSITIVE LOGITS
    𝙧
    3.66
    eaa
    3.37
    econ
    3.26
    𝙢
    3.24
    𝙜
    3.13
    ेत
    2.99
    ოგ
    2.96
    abay
    2.94
    eig
    2.93
    eket
    2.92
    Activations Density 0.343%

    No Known Activations