© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14519
    Prev
    Next
    INDEX
    Explanations

    kill, property, independently, more

    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
     և
    1.30
     ->
    1.28
    的游戏
    1.25
    ناط
    1.22
    和
    1.22
     
    1.21
     (‘
    1.21
    そして
    1.18
    pier
    1.17
    智
    1.16
    POSITIVE LOGITS
     Luc
    1.23
    żyć
    1.21
    ERY
    1.18
    ścic
    1.14
    ಮಾ
    1.12
    লীর
    1.11
    ansson
    1.11
    λα
    1.10
    OLYBD
    1.10
     OCLC
    1.09
    Activations Density 0.000%

    No Known Activations