© 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-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 743
    Prev
    Next
    INDEX
    Explanations

    the classic or 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_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
     for
    1.02
    на
    0.80
    >
    0.80
    <0x80>
    0.77
    ١
    0.75
    u
    0.73
    ’
    0.73
    AZIONE
    0.72
    w
    0.71
    ча
    0.70
    POSITIVE LOGITS
    0.82
     is
    0.76
     उमर
    0.73
    い
    0.71
    ïne
    0.66
     was
    0.66
    든
    0.65
    osevelt
    0.65
    hton
    0.65
     Ulster
    0.65
    Activations Density 0.002%

    No Known Activations