© 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. 23799
    Prev
    Next
    INDEX
    Explanations

    in dating apps

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

    html code snippets

    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
    ا
    1.06
    ların
    0.96
    کش
    0.93
    m
    0.93
    ה
    0.92
    \
    0.91
    _
    0.90
    ۵
    0.90
    k
    0.89
    f
    0.88
    POSITIVE LOGITS
    ي
    0.95
    <0x80>
    0.88
    in
    0.86
     مي
    0.82
    ：
    0.82
    امي
    0.80
     no
    0.79
    কাতা
    0.79
    نا
    0.78
    就
    0.78
    Activations Density 0.003%

    No Known Activations