© 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. 15839
    Prev
    Next
    INDEX
    Explanations

    concepts and subjective experiences

    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
     stadion
    1.17
     ยก
    1.13
    ებისა
    1.07
     provinces
    1.04
     स
    1.03
     येथील
    1.00
     province
    0.98
     vua
    0.98
    改革
    0.98
     expansion
    0.98
    POSITIVE LOGITS
    Cooldown
    1.16
    who
    1.14
     hábito
    1.09
    тивного
    1.08
     behov
    1.04
    í
    1.03
    erequisite
    1.03
     desiderio
    1.03
     espírito
    1.02
    Heter
    1.02
    Activations Density 0.110%

    No Known Activations