© 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. 10-GEMMASCOPE-RES-131K
    4. 80694
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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_10/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
    :
    -1.79
    廛
    -1.73
    خدا
    -1.71
    appellant
    -1.61
     inspiração
    -1.60
    همه
    -1.56
     any
    -1.56
    Koordinaten
    -1.55
     dealloc
    -1.55
    ݯ
    -1.53
    POSITIVE LOGITS
    6
    1.84
    5
    1.72
    2
    1.70
    \
    1.55
    3
    1.52
    7
    1.47
    signia
    1.40
    
    1.37
    }$,
    1.36
    ytale
    1.36
    Activations Density 0.104%

    No Known Activations