© 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. 54402
    Prev
    Next
    INDEX
    Explanations

    code structure `this.` or `.` access

    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
     nových
    -1.25
     Suomessa
    -1.21
     навіть
    -1.20
     regeringen
    -1.14
     nawet
    -1.14
     даже
    -1.13
    dozer
    -1.09
    wki
    -1.09
     három
    -1.06
     heilig
    -1.05
    POSITIVE LOGITS
     when
    1.05
     which
    1.03
     amidst
    0.96
     this
    0.96
     principally
    0.96
     proved
    0.95
    けれ
    0.95
     created
    0.94
     zile
    0.93
     because
    0.92
    Activations Density 0.006%

    No Known Activations