© 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. 83682
    Prev
    Next
    INDEX
    Explanations

    either, либо

    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
     or
    -2.03
     which
    -1.86
     &
    -1.77
     also
    -1.68
     також
    -1.66
    といいます
    -1.63
     Where
    -1.60
    1
    -1.55
     unteren
    -1.51
    i
    -1.51
    POSITIVE LOGITS
     入っ
    2.03
    bringing
    1.88
    obviously
    1.87
     })}
    1.84
    ♪♪
    1.82
    ꯱
    1.74
    嗱
    1.71
     })
    1.70
    ☆☆☆
    1.70
    during
    1.70
    Activations Density 0.027%

    No Known Activations