© 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. 4310
    Prev
    Next
    INDEX
    Explanations

    specific efforts warfare

    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
     tangerine
    1.16
     booting
    1.13
     تھی۔
    1.13
     savages
    1.13
     Yates
    1.11
     Helix
    1.10
    .].
    1.10
     Balfour
    1.07
     carriage
    1.07
    獼
    1.06
    POSITIVE LOGITS
     அதிகரிக்க
    1.17
    Homework
    1.17
    ீர்க
    1.11
    alloc
    1.10
     தவிர்க்க
    1.10
     öner
    1.08
     ngủ
    1.07
    Suggested
    1.04
     propose
    1.03
    خصص
    1.03
    Activations Density 0.000%

    No Known Activations