© 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. 4094
    Prev
    Next
    INDEX
    Explanations

    Reg, subject, Neuro followed by Exp, is, science

    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
     housewives
    0.95
     giphy
    0.84
    inprogress
    0.83
    诹
    0.81
    医療
    0.81
     عوام
    0.80
     музы
    0.80
     Veget
    0.80
    勳
    0.80
    getProgress
    0.80
    POSITIVE LOGITS
    łka
    0.84
    정과
    0.83
    이랑
    0.82
    łki
    0.82
     chip
    0.81
    자와
    0.81
     +
    0.81
     Rift
    0.81
     Siem
    0.79
     Aber
    0.79
    Activations Density 1.309%

    No Known Activations