© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218885
    Prev
    Next
    INDEX
    Explanations

    tracking engagement

    np_acts-logits-general · gemini-2.5-flash-lite

    rural Montana businesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    t
    0.58
    um
    0.56
    ens
    0.56
    ut
    0.54
    ü
    0.52
    serie
    0.52
    un
    0.52
    fert
    0.52
    ul
    0.51
    ’
    0.50
    POSITIVE LOGITS
    ടാ
    0.46
    Ỉ
    0.43
    קי
    0.42
    FundMe
    0.42
    חות
    0.41
    رمین
    0.41
     obliquely
    0.41
    ખા
    0.41
    жке
    0.41
    機会
    0.41
    Activations Density 0.000%

    No Known Activations