© 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. 1139
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and states

    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
     its
    -1.43
     which
    -1.42
     besonders
    -1.34
    轶
    -1.34
     jste
    -1.30
    倶
    -1.30
     on
    -1.28
     this
    -1.24
    ність
    -1.24
     unusually
    -1.23
    POSITIVE LOGITS
    5
    1.73
    3
    1.68
    6
    1.65
    コスパ
    1.52
    2
    1.46
     薬局
    1.44
    4
    1.44
    色んな
    1.40
    色々
    1.38
    8
    1.38
    Activations Density 0.140%

    No Known Activations