© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2434
    Prev
    Next
    INDEX
    Explanations

    multilingual explanations

    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_17_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
    (../
    1.16
    imeric
    1.12
    émico
    1.12
    émica
    1.11
    lyan
    1.09
     ဆ
    1.09
    aniach
    1.07
    uları
    1.06
    叓
    1.05
    騇
    1.05
    POSITIVE LOGITS
    O
    0.84
    o
    0.83
    C
    0.76
    S
    0.75
    s
    0.74
    R
    0.73
    r
    0.71
    c
    0.68
    i
    0.66
    I
    0.66
    Activations Density 0.153%

    No Known Activations