© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14651
    Prev
    Next
    INDEX
    Explanations

    as possible

    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_7_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
    ゥ
    2.58
    ా
    2.48
    ed
    2.39
    ാ
    2.25
    orious
    2.22
    dik
    2.21
    ා
    2.21
    滔
    2.20
    t
    2.19
    s
    2.19
    POSITIVE LOGITS
    𝐠
    2.62
    ERI
    2.56
    ᴍ
    2.55
    ্লিশ
    2.44
    ERON
    2.33
    ખા
    2.29
    𝐡
    2.23
    getInput
    2.22
    ishi
    2.21
    brack
    2.21
    Activations Density 0.058%

    No Known Activations