© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27132
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and abstract variables

    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
    Not in Any Lists

    No Comments

    Negative Logits
    anglicky
    -1.25
     obtuvo
    -1.15
     wirklich
    -1.13
     demuestra
    -1.11
     continúa
    -1.08
     hará
    -1.06
     recomienda
    -1.06
     стал
    -1.02
     again
    -1.02
     a
    -1.02
    POSITIVE LOGITS
     who
    1.26
    datable
    1.22
     república
    1.15
     που
    1.13
    uyasha
    1.12
    ᵗ
    1.10
     Baños
    1.10
     Andalucía
    1.09
    窥
    1.07
     whose
    1.06
    Activations Density 0.065%

    No Known Activations