© 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. 19677
    Prev
    Next
    INDEX
    Explanations

    regex special characters

    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
    噚
    -2.97
    哢
    -2.84
    ſſer
    -2.69
    >);
    -2.69
    鲼
    -2.63
    嚶
    -2.59
     bizim
    -2.52
     pentru
    -2.48
    Ꮉ
    -2.48
    ちゃんの
    -2.44
    POSITIVE LOGITS
    "
    4.03
    4
    3.88
    3
    3.69
    8
    3.39
    amp
    3.28
    9
    3.28
    1
    3.25
    >
    3.16
    6
    3.06
    2
    3.02
    Activations Density 0.003%

    No Known Activations