© 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. 22-GEMMASCOPE-RES-131K
    7. 25074
    Prev
    Next
    INDEX
    Explanations

    indicating origin or source

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     גם
    -1.34
    <bos>
    -1.24
     inalámb
    -1.21
     tetap
    -1.18
     dve
    -1.16
    because
    -1.14
     pintor
    -1.14
    }
    -1.13
     także
    -1.13
    も
    -1.13
    POSITIVE LOGITS
    ,
    1.51
     henceforth
    1.48
     standpoint
    1.38
    大多
    1.30
     to
    1.27
    .
    1.25
     afar
    1.22
    They
    1.21
    But
    1.20
     They
    1.19
    Activations Density 0.028%

    No Known Activations