© 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. 34-GEMMASCOPE-RES-131K
    7. 106367
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, indices, and suffixes

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    |_{\
    -1.42
    ]_{\
    -1.27
     لهذه
    -1.24
     فيها
    -1.23
     στην
    -1.12
     }_{\
    -1.12
    _\
    -1.11
     della
    -1.08
     nella
    -1.07
     _{\
    -1.06
    POSITIVE LOGITS
     στο
    1.70
     στον
    1.57
     beim
    1.39
    Beim
    1.33
    }_{
    1.31
     del
    1.27
     του
    1.22
     Beim
    1.18
    beim
    1.16
    _{
    1.12
    Activations Density 0.047%

    No Known Activations