© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1795
    Prev
    Next
    INDEX
    Explanations

    date, time, location

    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_65k_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
    s
    0.91
    ↵
    0.74
    ↵↵
    0.72
    .
    0.66
     you
    0.63
    t
    0.62
    ...
    0.60
    …
    0.60
    )
    0.58
    e
    0.57
    POSITIVE LOGITS
    𒄖
    1.67
    𒆗
    1.66
    𒊓
    1.66
    𒈩
    1.64
    𒉈
    1.63
    𒌐
    1.62
    𒅕
    1.62
    𒀖
    1.62
    𒄠
    1.61
    𒀯
    1.61
    Activations Density 1.021%

    No Known Activations