© 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. 10-GEMMASCOPE-RES-131K
    7. 39152
    Prev
    Next
    INDEX
    Explanations

    educating people

    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
     '
    -2.91
    
    -2.41
     nieuwe
    -2.41
    बाइल
    -2.38
    鲽
    -2.23
    ￨
    -2.20
     nové
    -2.16
    数を
    -2.03
     lament
    -2.03
    nóstico
    -2.03
    POSITIVE LOGITS
    .
    3.55
    !’
    2.55
    0
    2.53
    甞
    2.11
     fashioned
    2.11
    ’,
    2.09
    ’’
    2.09
     проблему
    2.06
    …’
    2.05
    *
    2.05
    Activations Density 0.005%

    No Known Activations