© 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. 10-GEMMASCOPE-RES-131K
    7. 14890
    Prev
    Next
    INDEX
    Explanations

    resource and collection names

    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
    ætter
    -1.61
    thical
    -1.53
    öffnet
    -1.53
    鴟
    -1.52
    ⎔
    -1.52
    怍
    -1.51
    泚
    -1.50
    蛏
    -1.50
     organisme
    -1.48
    搋
    -1.46
    POSITIVE LOGITS
    Since
    2.17
    Because
    2.06
     the
    1.98
    Both
    1.88
    Many
    1.76
    Probably
    1.75
    Without
    1.72
    Putting
    1.70
    9
    1.68
     both
    1.64
    Activations Density 0.006%

    No Known Activations