© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12276
    Prev
    Next
    INDEX
    Explanations

    brow furrowed

    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
    /
    0.93
    -
    0.82
     meilleures
    0.80
     par
    0.79
     oil
    0.77
     A
    0.73
     dead
    0.71
    ्व
    0.70
    তি
    0.69
    या
    0.69
    POSITIVE LOGITS
    匏
    1.16
    疃
    1.15
    扆
    1.14
    罾
    1.12
    Morris
    1.08
     Unwin
    1.06
    indari
    1.05
    usetts
    1.04
     保存
    1.04
    쮿
    1.04
    Activations Density 0.001%

    No Known Activations