© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    one at a time

    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
    protect
    2.22
    er
    2.02
    l
    1.92
    ls
    1.90
    or
    1.89
    lk
    1.88
     protect
    1.85
    tot
    1.85
    lle
    1.84
    inten
    1.80
    POSITIVE LOGITS
     instalaciones
    1.89
    ಿಯಲ್ಲಿ
    1.88
    ）.
    1.83
    opuerto
    1.82
     thở
    1.77
     showAlert
    1.72
     indicadores
    1.68
    ↵↵↵↵↵↵↵↵
    1.67
    KindOfClass
    1.66
     Metropolitana
    1.66
    Activations Density 0.000%

    No Known Activations