© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5556
    Prev
    Next
    INDEX
    Explanations

    python flask code

    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
    ́t
    2.53
     defaultstate
    2.47
    <bos>
    2.35
    ្វ
    2.31
    ExpNow
    2.22
    ्य
    2.12
    呋
    2.12
    GroupLayout
    2.09
    ته
    2.08
    etimes
    2.07
    POSITIVE LOGITS
    _.
    2.51
    g
    2.48
    ICON
    2.46
    WEBPACK
    2.44
    gib
    2.39
    gow
    2.38
    뉘
    2.23
    inkl
    2.20
    বেদন
    2.14
     oszt
    2.11
    Activations Density 0.004%

    No Known Activations