© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73162
    Prev
    Next
    INDEX
    Explanations

    direct modifier

    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
    {
    -3.64
     

    -2.73
    ("
    -2.61
                
    -2.42
     haupts
    -2.36
    ––
    -2.36
    等我
    -2.33
    …
    -2.33
     “
    -2.31
     ….
    -2.27
    POSITIVE LOGITS
    縯
    2.78
    ......”
    2.77
    🌻
    2.52
    ”，
    2.50
     groet
    2.48
    💞
    2.44
    𖥦
    2.42
    玧
    2.41
     現貨
    2.39
    ⚾
    2.39
    Activations Density 0.027%

    No Known Activations