© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3981
    Prev
    Next
    INDEX
    Explanations

    empty list, array, or dictionary

    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
    Negative Logits
     fluid
    1.82
     Fluid
    1.63
    vich
    1.58
     quasip
    1.56
     fluids
    1.56
    тивно
    1.55
    ሽ
    1.54
     polynomials
    1.54
     continuum
    1.54
     gesture
    1.53
    POSITIVE LOGITS
    港
    2.45
    landing
    2.40
     chargingStation
    2.36
     مدينة
    2.35
    airport
    2.26
    傊
    2.25
    地点
    2.22
    tempat
    2.21
     kampus
    2.20
    䢙
    2.20
    Activations Density 0.353%

    No Known Activations