© 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. 24048
    Prev
    Next
    INDEX
    Explanations

    carbon footprint, Grande Valley, Lives Matter, disciples

    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
     Because
    -1.80
    豋
    -1.73
    」、
    -1.71
     our
    -1.69
     Regardless
    -1.66
    琹
    -1.60
     Like
    -1.60
     With
    -1.59
     wre
    -1.59
    为了
    -1.56
    POSITIVE LOGITS
    generally
    1.81
     .......
    1.76
     ........
    1.76
    ޏ
    1.63
     .........
    1.62
     NEW
    1.60
    蟊
    1.59
     pask
    1.57
     ort
    1.55
    mostly
    1.54
    Activations Density 0.046%

    No Known Activations