© 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. 6972
    Prev
    Next
    INDEX
    Explanations

    to explain

    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
    G
    1.15
    ik
    1.14
    Y
    1.12
    D
    1.12
    M
    1.11
    T
    1.11
    F
    1.11
    S
    1.11
    yt
    1.10
    R
    1.09
    POSITIVE LOGITS
    <unused1055>
    1.40
    <unused727>
    1.40
    <unused1125>
    1.40
    <unused905>
    1.39
    owlapi
    1.38
    <unused967>
    1.37
    <unused920>
    1.36
    <unused145>
    1.35
    <unused932>
    1.34
    <unused138>
    1.33
    Activations Density 0.008%

    No Known Activations