© 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. 34-GEMMASCOPE-RES-131K
    4. 90154
    Prev
    Next
    INDEX
    Explanations

    programming extensions

    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
     promptly
    -0.88
     efficiently
    -0.87
     swiftly
    -0.85
     strangely
    -0.84
     more
    -0.81
     jantung
    -0.81
     effective
    -0.77
     instantly
    -0.77
     reasonably
    -0.77
     quickly
    -0.77
    POSITIVE LOGITS
    wanted
    0.88
    outre
    0.85
    icec
    0.83
     fizeram
    0.82
    verne
    0.82
    ージェ
    0.81
    abstractmethod
    0.80
    🙎
    0.78
    told
    0.78
     малень
    0.77
    Activations Density 0.003%

    No Known Activations