© 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. 7313
    Prev
    Next
    INDEX
    Explanations

    direct impact, revenue, interview, attacks

    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
    los
    1.91
    鹂
    1.69
    discos
    1.63
    toned
    1.60
    ctree
    1.60
    ften
    1.52
    ition
    1.52
    <unused1738>
    1.51
    ২১
    1.51
    েন্টি
    1.50
    POSITIVE LOGITS
    바로
    1.48
    直
    1.47
     сердце
    1.47
     Націона
    1.41
    嚨
    1.41
     Perc
    1.35
    aneamente
    1.34
     Core
    1.34
    ⓵
    1.30
     Concentrations
    1.30
    Activations Density 0.226%

    No Known Activations