© 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. 84930
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

    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
     piemē
    -0.81
    SCAN
    -0.77
     stung
    -0.76
    Зноскі
    -0.74
     lil
    -0.74
    iguar
    -0.73
    这座
    -0.72
    tze
    -0.71
    Scanning
    -0.71
    Jimmy
    -0.71
    POSITIVE LOGITS
     选择
    0.77
     piaci
    0.76
     Ashby
    0.76
    🦶
    0.75
     mandar
    0.75
    Workspace
    0.73
     Анна
    0.72
     Hadd
    0.72
    AILABLE
    0.72
     चाल
    0.71
    Activations Density 0.019%

    No Known Activations