© 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. 34-GEMMASCOPE-RES-131K
    7. 70236
    Prev
    Next
    INDEX
    Explanations

    Neuropsychological`, `morestats`, `perspectives on`

    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
     Balkan
    -0.78
    dotta
    -0.75
    三次
    -0.75
     tredje
    -0.74
    Alicia
    -0.73
    парат
    -0.73
    虹
    -0.73
     adjourned
    -0.72
    ními
    -0.72
     derail
    -0.71
    POSITIVE LOGITS
    omers
    0.90
     arrays
    0.84
    多吃
    0.78
     enfe
    0.77
    array
    0.74
     array
    0.74
     eftersom
    0.74
     arr
    0.73
    omer
    0.72
    arr
    0.72
    Activations Density 0.021%

    No Known Activations