© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13011
    Prev
    Next
    INDEX
    Explanations

    what to do

    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_7_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
    maları
    2.62
    nbr
    2.46
    cą
    2.36
    귿
    2.34
     ঝামে
    2.32
    substantial
    2.25
    kannya
    2.25
     fác
    2.24
    ರ್ಚ
    2.24
    summ
    2.23
    POSITIVE LOGITS
     confirmed
    2.02
     seat
    1.92
    ście
    1.86
     treated
    1.82
     seats
    1.73
     footh
    1.66
     to
    1.64
    ,
    1.62
     guardian
    1.48
    ised
    1.48
    Activations Density 0.052%

    No Known Activations