Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3079
    Prev
    Next
    INDEX
    Explanations

    explaining information or troubleshooting

    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
    <unused1187>
    1.67
     Investigación
    1.66
    [multimodal]
    1.65
     Voucher
    1.65
    <unused412>
    1.64
    Databaze
    1.64
    <unused736>
    1.63
     Lecturer
    1.62
    bindingFields
    1.60
    Š
    1.60
    POSITIVE LOGITS
    on
    1.26
    u
    1.21
    к
    1.14
    F
    1.12
    un
    1.10
    f
    1.08
    dom
    1.08
    us
    1.03
    os
    1.03
    T
    1.01
    Activations Density 0.000%

    No Known Activations