© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40280
    Prev
    Next
    INDEX
    Explanations

    concern for or with

    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
    ẨM
    -1.60
    ङ
    -1.60
    祤
    -1.55
     campañas
    -1.52
    傒
    -1.48
    不一樣
    -1.45
     mūsų
    -1.45
    Menurutnya
    -1.44
     mencionado
    -1.41
    靦
    -1.41
    POSITIVE LOGITS
    ↵↵
    1.80
    </strong>
    1.56
    the
    1.55
    men
    1.52
    at
    1.42
     
    1.42
    </em>
    1.34
    m
    1.34
    in
    1.34
    </h3>
    1.30
    Activations Density 0.032%

    No Known Activations