© 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. 15869
    Prev
    Next
    INDEX
    Explanations

    customization options and instructions

    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
     Dris
    1.31
    Subscribe
    1.28
     fucking
    1.25
    ⁢
    1.22
     onlookers
    1.21
     multicolored
    1.20
     basically
    1.19
     castor
    1.19
    ⁤
    1.19
     banget
    1.18
    POSITIVE LOGITS
     иной
    1.15
    良好的
    1.12
     улуч
    1.08
     доб
    1.03
     хорошие
    1.01
    改善
    1.01
     низ
    1.01
     прекра
    0.99
     высоких
    0.98
     개선
    0.98
    Activations Density 0.074%

    No Known Activations