© 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
    2. Gemma-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 971
    Prev
    Next
    INDEX
    Explanations

    npm install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مار
    0.69
    箐
    0.61
    Kon
    0.61
     Kon
    0.60
    Кон
    0.57
     Кон
    0.57
     kon
    0.55
     מו
    0.55
     corte
    0.54
     活動
    0.54
    POSITIVE LOGITS
     పు
    0.55
    forward
    0.53
    로운
    0.53
     Weibo
    0.52
    <0xC5>
    0.51
    Subgraph
    0.51
    fila
    0.51
    로나
    0.50
     fred
    0.50
     Liberation
    0.50
    Activations Density 0.599%

    No Known Activations