© 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. 7374
    Prev
    Next
    INDEX
    Explanations

    geopolitical regions or continents

    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
    новништво
    1.18
    ཀ
    0.99
    iox
    0.98
    ዞ
    0.95
    ধান
    0.94
    бера
    0.94
    ě
    0.93
    ัจ
    0.92
    बांग
    0.92
    コード
    0.92
    POSITIVE LOGITS
     instrumental
    1.28
     mundane
    1.27
     civilian
    1.25
     instructional
    1.25
     relat
    1.24
     proactive
    1.23
     loyal
    1.22
     FIX
    1.22
     civil
    1.20
     motivational
    1.20
    Activations Density 0.040%

    No Known Activations