© 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. 111780
    Prev
    Next
    INDEX
    Explanations

    adds plus

    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
     it
    -1.84
    姈
    -1.63
     of
    -1.63
    ี
    -1.59
    replyreport
    -1.57
    んや
    -1.57
    VERTISEMENT
    -1.52
    忸
    -1.52
     membaca
    -1.48
     αυτά
    -1.48
    POSITIVE LOGITS
     "
    2.16
     
    2.00
     \&
    1.80
     '
    1.72
    “
    1.70
    ↵↵↵
    1.70
     PLUS
    1.69
     -
    1.59
    ",
    1.59
    Chances
    1.57
    Activations Density 0.014%

    No Known Activations