© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84661
    Prev
    Next
    INDEX
    Explanations

    among other things

    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
    了一个
    -1.32
     attempt
    -1.27
    一个
    -1.18
     same
    -1.17
    出来ました
    -1.14
    姦
    -1.13
    遑
    -1.13
     komplette
    -1.13
     two
    -1.10
    ıyordu
    -1.08
    POSITIVE LOGITS
     the
    1.96
     annat
    1.64
     those
    1.61
     other
    1.59
     them
    1.55
     andet
    1.50
     annet
    1.48
     otras
    1.45
     others
    1.32
    Otras
    1.27
    Activations Density 0.023%

    No Known Activations