© 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. 22-GEMMASCOPE-RES-131K
    7. 130713
    Prev
    Next
    INDEX
    Explanations

    shake it

    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
     They
    -2.64
    s
    -2.47
     But
    -2.44
     painstaking
    -2.42
     mistaken
    -2.38
     rea
    -2.30
        
    -2.19
     w
    -2.14
     cancelamento
    -2.14
    <b>
    -2.13
    POSITIVE LOGITS
    虓
    2.80
     ekstra
    2.78
     konsep
    2.77
     eksklu
    2.72
    骝
    2.69
     ekst
    2.67
     metode
    2.67
     maksimum
    2.61
     pandemi
    2.59
     teori
    2.58
    Activations Density 0.010%

    No Known Activations