© 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. 32700
    Prev
    Next
    INDEX
    Explanations

    technical terms and their context

    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
    2
    -1.37
     in
    -1.27
     recomienda
    -1.16
     môžete
    -1.13
     einstellen
    -1.13
     immorality
    -1.12
    1
    -1.07
     budete
    -1.06
     nemá
    -1.06
     beetje
    -1.05
    POSITIVE LOGITS
     vores
    1.28
     ‚
    1.28
    ┬
    1.27
     detta
    1.23
     अगर
    1.21
     degli
    1.20
     тобой
    1.17
    ñales
    1.16
    "]));
    1.16
    𝗣
    1.15
    Activations Density 0.117%

    No Known Activations