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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 404
    Prev
    Next
    INDEX
    Explanations

    Uni, row, via, EV

    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_13_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
     spokesperson
    0.97
    彙
    0.96
     live
    0.94
     reunion
    0.93
    ifter
    0.92
     했을
    0.92
    IFT
    0.91
     ascending
    0.91
     airspace
    0.91
    agma
    0.90
    POSITIVE LOGITS
     бо
    1.04
     sayıda
    1.04
     чолові
    0.99
     أو
    0.99
     ولم
    0.99
     kulit
    0.98
     س
    0.97
     lång
    0.96
     çeşitli
    0.95
     liquides
    0.94
    Activations Density 0.000%

    No Known Activations