© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9745
    Prev
    Next
    INDEX
    Explanations

    of states and cities

    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_22_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
    ྣ
    1.07
    JSONArray
    0.95
    orian
    0.90
     cuentan
    0.90
    כות
    0.87
     तहत
    0.86
    ší
    0.85
    餮
    0.84
    قات
    0.84
    銳
    0.83
    POSITIVE LOGITS
    ورسٹی
    1.12
    Universität
    1.00
    iversity
    0.99
     casilla
    0.96
    대학교
    0.92
     photocopying
    0.91
    nivers
    0.91
     hypergeometric
    0.89
     germanium
    0.89
     captcha
    0.88
    Activations Density 0.014%

    No Known Activations