© 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
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2382
    Prev
    Next
    INDEX
    Explanations

    of that nature

    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_13_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
     her
    1.12
    her
    1.10
     сві
    1.00
    eyer
    0.94
    aan
    0.91
    their
    0.91
    arma
    0.89
    踏
    0.89
     xuống
    0.88
    maria
    0.88
    POSITIVE LOGITS
     sorts
    1.87
     рода
    1.61
    長さ
    1.55
     caliber
    1.53
     calibre
    1.52
     tipo
    1.50
    TYPE
    1.47
     tamanho
    1.47
    ประเภท
    1.46
     HUOBI
    1.43
    Activations Density 0.412%

    No Known Activations