© 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. 13847
    Prev
    Next
    INDEX
    Explanations

    connecting issues and inputs

    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
     također
    1.19
     найбіль
    1.10
     тоже
    1.06
     관련된
    1.06
     також
    1.04
     др
    1.04
    亦
    1.03
    ریر
    1.02
    PERT
    1.01
     също
    1.00
    POSITIVE LOGITS
     and
    3.09
     và
    2.85
    and
    2.82
     и
    2.75
     और
    2.62
     এবং
    2.60
     และ
    2.59
     आणि
    2.50
    และ
    2.47
     και
    2.44
    Activations Density 1.457%

    No Known Activations