© 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-16K
    7. 1338
    Prev
    Next
    INDEX
    Explanations

    a [noun/identifier]

    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
    that
    1.47
    to
    1.45
     it
    1.30
     to
    1.28
    The
    1.28
    र
    1.27
    and
    1.25
    gives
    1.24
    gave
    1.24
    د
    1.24
    POSITIVE LOGITS
     member
    1.29
     cikin
    1.19
     människor
    1.14
     vét
    1.14
    勬
    1.13
     busy
    1.13
    ureen
    1.13
    <bos>
    1.12
    ートン
    1.12
     mennesker
    1.11
    Activations Density 0.280%

    No Known Activations