© 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. 129791
    Prev
    Next
    INDEX
    Explanations

    cooking pans and cookware

    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
    ’
    -1.88
    鏨
    -1.76
    ведений
    -1.73
     abiye
    -1.72
    ﹶ
    -1.69
     köpek
    -1.66
    ांकि
    -1.65
     lakini
    -1.65
    )’
    -1.59
    Ꮟ
    -1.58
    POSITIVE LOGITS
    ."
    2.23
    蟥
    2.02
     distintas
    1.95
     ร์
    1.79
    ".
    1.78
    灯光
    1.77
     :).
    1.74
    珦
    1.73
    意思是
    1.73
     suo
    1.73
    Activations Density 0.005%

    No Known Activations