© 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. 7989
    Prev
    Next
    INDEX
    Explanations

    911 or your local emergency number

    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
     boon
    1.10
    껭
    1.07
    坦
    0.99
     retrouver
    0.98
    yim
    0.96
     whol
    0.96
     overcoming
    0.94
     cleansing
    0.93
    ັດ
    0.93
     jaundice
    0.93
    POSITIVE LOGITS
     металли
    1.25
     Бу
    1.18
     бога
    1.15
    Бу
    1.11
    гу
    1.09
     На
    1.09
    Ю
    1.08
    На
    1.07
     Kubernetes
    1.06
     Администра
    1.06
    Activations Density 0.068%

    No Known Activations