© 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. 13764
    Prev
    Next
    INDEX
    Explanations

    words starting with wh

    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
    ”
    -3.27
    .’
    -3.06
    ,’
    -2.86
    ’
    -2.83
     \
    -2.81
     consentimento
    -2.80
     cancelamento
    -2.77
    ,"
    -2.48
     looks
    -2.42
    ’,
    -2.42
    POSITIVE LOGITS
    酲
    2.42
    itizing
    2.31
     {
    
    
    2.30
    TemporalType
    2.25
    itisation
    2.20
     लिए
    2.20
     contiennent
    2.19
    ጧ
    2.17
    itized
    2.17
    краси
    2.16
    Activations Density 0.021%

    No Known Activations