© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    coordinating actions and systems

    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
    ಿ
    1.72
    粈
    1.70
     ausreiche
    1.69
     vattum
    1.67
    过
    1.66
    يلا
    1.63
     فونیټ
    1.63
     hetuk
    1.63
    ុ
    1.62
     hObject
    1.61
    POSITIVE LOGITS
     North
    1.37
     Lake
    1.24
     en
    1.23
    ay
    1.23
    ica
    1.22
     Mayor
    1.22
     En
    1.20
     leaders
    1.20
     north
    1.20
    ry
    1.19
    Activations Density 0.134%

    No Known Activations