© 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. 813
    Prev
    Next
    INDEX
    Explanations

    data and information

    np_acts-logits-general · gemini-2.5-flash-lite

    data storage

    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
     I
    1.20
    ot
    1.02
     आईआई
    0.99
    är
    0.91
    icks
    0.82
    usten
    0.82
     आई
    0.81
     TIME
    0.81
    "،
    0.79
    рі
    0.78
    POSITIVE LOGITS
    a
    1.86
    n
    1.74
    f
    1.73
    <0x80>
    1.27
    사
    1.23
    i
    1.22
    ي
    1.21
    m
    1.20
    r
    1.15
    ه
    1.15
    Activations Density 0.791%

    No Known Activations