© 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. 34-GEMMASCOPE-RES-131K
    7. 117852
    Prev
    Next
    INDEX
    Explanations

    parenthetical information

    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_34/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
    场地
    -0.87
    帰る
    -0.79
     NORTH
    -0.77
    LITER
    -0.76
    ꯵
    -0.72
    त्ता
    -0.71
     북
    -0.71
    远离
    -0.70
    ensibility
    -0.70
     northwestern
    -0.70
    POSITIVE LOGITS
    είτε
    0.95
     semi
    0.92
    天下
    0.89
     dieną
    0.89
    แบบ
    0.89
     Архивировано
    0.87
    fattning
    0.86
    lichkeiten
    0.85
     non
    0.85
    靼
    0.85
    Activations Density 0.110%

    No Known Activations