© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11832
    Prev
    Next
    INDEX
    Explanations

    SCP, Dalai Lama, placebo

    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
    locatorType
    2.34
    dokkaHtml
    1.76
    empot
    1.71
    駑
    1.67
    addPreferred
    1.66
     catchment
    1.66
     externalities
    1.65
     znam
    1.64
     trends
    1.63
    örter
    1.63
    POSITIVE LOGITS
    tw
    1.72
    ことが
    1.69
    t
    1.68
    ्ट
    1.64
     Pink
    1.58
    Pink
    1.57
     nicknamed
    1.54
    <b>
    1.51
     Dev
    1.50
     Avery
    1.48
    Activations Density 0.043%

    No Known Activations