© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98441
    Prev
    Next
    INDEX
    Explanations

    assignments and comparisons

    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
     a
    -1.12
     apparti
    -1.11
    って思
    -1.05
    蚍
    -1.03
     capuz
    -1.03
     linho
    -1.02
    を使用
    -1.01
    zeigt
    -1.01
     asfal
    -1.00
    indicates
    -1.00
    POSITIVE LOGITS
     this
    1.20
     in
    1.19
     from
    1.15
    ∏
    0.95
    ⌀
    0.93
     but
    0.91
     that
    0.91
    eaways
    0.90
     الدم
    0.89
    了你
    0.88
    Activations Density 0.002%

    No Known Activations