© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 336
    Prev
    Next
    INDEX
    Explanations

    A basic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    s
    1.34
    RX
    1.30
    et
    1.28
    с
    1.20
    RR
    1.17
    TG
    1.17
    RK
    1.16
    ों
    1.14
    RG
    1.13
    TOR
    1.13
    POSITIVE LOGITS
    ৯
    1.31
    ні
    1.21
    ки
    1.11
    ക്ക്
    1.07
    ්
    1.04
    ação
    1.03
     davran
    1.03
    erweise
    1.02
    টা
    1.02
    zelfde
    1.00
    Activations Density 0.701%

    No Known Activations