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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70622
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax

    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
     AdapterView
    -1.05
     pecu
    -1.05
     WaitForSeconds
    -1.02
     Katal
    -1.02
    瓷
    -1.00
    臵
    -0.93
     Femme
    -0.93
    uaire
    -0.91
     ferti
    -0.91
     ENGINEERS
    -0.91
    POSITIVE LOGITS
     and
    1.13
     also
    0.99
     before
    0.84
    Polska
    0.80
     this
    0.79
    の詳細
    0.78
    encana
    0.77
    .
    0.76
     its
    0.75
     it
    0.74
    Activations Density 0.001%

    No Known Activations