© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38544
    Prev
    Next
    INDEX
    Explanations

    state or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -1.44
     furthermore
    -1.38
     further
    -1.31
     another
    -1.30
     subsequently
    -1.30
     specifically
    -1.28
     we
    -1.25
     additionally
    -1.20
     including
    -1.19
     using
    -1.18
    POSITIVE LOGITS
    因为它
    1.26
     only
    1.23
    …»
    1.15
     many
    1.12
    这意味着
    1.09
    ูก
    1.08
    .»
    1.08
    ₋
    1.05
    !»
    1.04
    ...»
    1.04
    Activations Density 0.200%

    No Known Activations