© 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. 10033
    Prev
    Next
    INDEX
    Explanations

    Executive Order, low concentrations, caffeine consumption

    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
     花
    1.21
     อังกฤษ
    1.18
     महा
    1.17
     和
    1.17
     دول
    1.17
     וא
    1.14
     女
    1.11
     法
    1.10
     وقل
    1.10
     noqa
    1.10
    POSITIVE LOGITS
    部の
    1.12
     Seite
    1.11
    বারের
    1.10
     Percolation
    1.10
    oretum
    1.09
    ্বার
    1.07
    Deleting
    1.05
     Reclamation
    1.04
    Specific
    1.02
     sij
    1.02
    Activations Density 0.000%

    No Known Activations