© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12010
    Prev
    Next
    INDEX
    Explanations

    Tim Berners-Lee

    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_7_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
     up
    2.14
     Bukh
    2.12
    <blockquote>
    1.96
    ing
    1.93
    」
    1.92
    .»
    1.89
     hen
    1.85
     bel
    1.84
    »
    1.84
    ந்து
    1.80
    POSITIVE LOGITS
    𝐨
    3.14
    𝐠
    2.90
    𝐚
    2.85
    𝐫
    2.78
    ির
    2.68
    𝐧
    2.67
    𝐢
    2.62
    𝐞
    2.58
    𝐩
    2.49
    𝚘
    2.48
    Activations Density 0.003%

    No Known Activations