© 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. 10665
    Prev
    Next
    INDEX
    Explanations

    work, is, indergarten, watched, operator, key, prompt

    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
    regation
    1.84
     समाजा
    1.65
     單
    1.58
     Eton
    1.58
     POR
    1.56
     निर्णया
    1.56
     Albums
    1.55
     ኤ
    1.54
     entscheiden
    1.49
    ათ
    1.48
    POSITIVE LOGITS
    arakatuh
    2.05
    rafish
    1.97
    cyon
    1.95
     coscienza
    1.93
    নিষ্ঠ
    1.89
    англ
    1.85
    <unused1807>
    1.85
    ная
    1.78
     lanceol
    1.77
    уга
    1.77
    Activations Density 0.000%

    No Known Activations