© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3027
    Prev
    Next
    INDEX
    Explanations

    visuals descriptions

    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
    اء
    2.03
    den
    1.95
     building
    1.95
     cooker
    1.83
     و
    1.71
    ია
    1.71
    г
    1.68
     chaff
    1.67
    endment
    1.67
     crest
    1.66
    POSITIVE LOGITS
    Melitaea
    2.63
    л
    2.60
    sia
    2.59
    ('./
    2.58
    INTRESOURCE
    2.56
    бычно
    2.56
    椂
    2.56
     '/',
    2.51
    ﮧ
    2.50
    sman
    2.48
    Activations Density 0.112%

    No Known Activations