© 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. 4152
    Prev
    Next
    INDEX
    Explanations

    History of Present Illness

    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
     tüm
    1.79
    <0xF3>
    1.70
     esfuerzos
    1.66
     Profits
    1.66
     diğer
    1.65
     también
    1.65
     aos
    1.61
     profundizar
    1.61
    The
    1.59
     também
    1.58
    POSITIVE LOGITS
    fireFlower
    1.42
    =_
    1.30
    coverageStat
    1.29
    akarane
    1.26
    вае
    1.26
    ногда
    1.24
    hiqdev
    1.22
    baseHP
    1.20
    datei
    1.19
    INSTDIR
    1.18
    Activations Density 0.053%

    No Known Activations