© 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. 8229
    Prev
    Next
    INDEX
    Explanations

    From Each According to His Need

    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
     以及
    1.63
     và
    1.54
     그리고
    1.53
     and
    1.51
     και
    1.49
     및
    1.48
     и
    1.45
     及
    1.40
    정과
    1.39
     અને
    1.39
    POSITIVE LOGITS
     Bure
    1.12
    leva
    1.02
     aparece
    1.02
     debería
    1.01
     lijkt
    1.01
    acă
    1.01
     dovrebbe
    0.99
     begint
    0.99
     disp
    0.98
     ilus
    0.98
    Activations Density 0.000%

    No Known Activations