© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6886
    Prev
    Next
    INDEX
    Explanations

    symbols and lists

    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
    agine
    2.25
    Different
    2.24
    Yesterday
    2.11
    ╡
    2.10
    িখিত
    2.10
    liegt
    2.07
    Designed
    2.07
    Enc
    2.06
    Cuenta
    2.05
    menuid
    2.03
    POSITIVE LOGITS
    ndash
    4.73
    amp
    4.55
    mdash
    4.25
    quot
    3.74
    nbs
    3.70
    𝑟
    3.62
    ldquo
    3.38
    middot
    3.25
    eacute
    3.21
    iacute
    3.19
    Activations Density 0.087%

    No Known Activations