© 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. 4178
    Prev
    Next
    INDEX
    Explanations

    questions followed by "well" or "sentiments"

    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
    '،
    2.02
    žen
    1.72
    സി
    1.66
    ',
    1.66
    뮬
    1.62
    ņas
    1.62
    že
    1.61
    /',
    1.61
     څ
    1.61
    حی
    1.60
    POSITIVE LOGITS
     confl
    1.65
     ventures
    1.57
     feliz
    1.52
    :”
    1.50
     venture
    1.49
     demonic
    1.48
    guild
    1.41
     utopian
    1.41
     guild
    1.40
     sinful
    1.38
    Activations Density 0.000%

    No Known Activations