© 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. 34-GEMMASCOPE-RES-131K
    7. 59696
    Prev
    Next
    INDEX
    Explanations

    programming generics

    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_34/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
    duire
    -0.77
     tokenId
    -0.75
    𝘶
    -0.72
    wich
    -0.69
    VIRONMENT
    -0.68
    یین
    -0.68
    ARIAN
    -0.68
     Corporal
    -0.67
    Marian
    -0.67
    idin
    -0.67
    POSITIVE LOGITS
     generic
    4.38
    generic
    3.73
    Generic
    3.67
     Generic
    3.66
     gener
    3.44
    generics
    3.31
    泛
    2.92
    GENERIC
    2.80
     Gener
    2.50
    Gener
    2.33
    Activations Density 0.117%

    No Known Activations