© 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. 34928
    Prev
    Next
    INDEX
    Explanations

    school levels

    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
    ଶ
    -1.24
    ないけど
    -1.20
     بايد
    -1.20
     telo
    -1.19
     vernac
    -1.19
    踯
    -1.14
     أثناء
    -1.13
    ⿷
    -1.12
     medica
    -1.11
     Tiss
    -1.11
    POSITIVE LOGITS
     school
    1.87
    ：……
    1.59
     children
    1.50
     esfuerzan
    1.48
     those
    1.38
     other
    1.34
     district
    1.30
     buildings
    1.21
     where
    1.20
     this
    1.20
    Activations Density 0.061%

    No Known Activations