© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8608
    Prev
    Next
    INDEX
    Explanations

    Debian/Ubuntu

    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_22_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
    حيان
    0.97
    INUS
    0.82
     full
    0.78
    statistic
    0.78
    extra
    0.77
    ·
    0.77
    levant
    0.75
     stereotyp
    0.74
    況
    0.74
     dawned
    0.72
    POSITIVE LOGITS
    ating
    1.00
    乀
    0.97
    resser
    0.92
    urring
    0.92
     সহযোগিতা
    0.91
    atem
    0.91
    imetro
    0.91
    imetre
    0.91
     engagements
    0.90
    ATING
    0.89
    Activations Density 0.035%

    No Known Activations