© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    contact address labels

    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
     conférence
    2.23
     garantiza
    2.16
    ሳሪያ
    2.06
    冧
    2.04
     supplementary
    2.04
     oración
    2.02
     bidang
    1.99
    hua
    1.98
    ňa
    1.97
     conseil
    1.97
    POSITIVE LOGITS
    лять
    1.47
     м
    1.38
    Jed
    1.38
     inhabiting
    1.37
    ಿಸ್ಟ
    1.36
    يع
    1.35
     rhythms
    1.35
     habit
    1.35
    ැල
    1.35
     reclaiming
    1.31
    Activations Density 0.123%

    No Known Activations