© 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. 3546
    Prev
    Next
    INDEX
    Explanations

    Experimental Psychology

    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
    ल्पनिक
    1.97
    €“
    1.91
    €™
    1.85
    ˜
    1.82
    ডেইলি
    1.79
    ష్ట
    1.78
    ać
    1.77
    kelijk
    1.76
    yd
    1.76
    Å
    1.70
    POSITIVE LOGITS
    ical
    2.06
     ';'
    1.99
    ⃛
    1.99
    olecular
    1.97
    ној
    1.96
    ICAL
    1.96
     ";"
    1.94
    িক
    1.92
    straat
    1.92
     সংখ্যক
    1.92
    Activations Density 0.028%

    No Known Activations