© 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. 50067
    Prev
    Next
    INDEX
    Explanations

    one of many

    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
     and
    -1.05
    ここ
    -0.92
     two
    -0.87
    sság
    -0.84
    tigheter
    -0.84
    𝑊
    -0.84
    endpush
    -0.83
     Ones
    -0.83
     hoeveel
    -0.82
     even
    -0.81
    POSITIVE LOGITS
     among
    1.67
     part
    1.66
     many
    1.63
     wielu
    1.59
     of
    1.56
    many
    1.51
     component
    1.44
     MANY
    1.39
     example
    1.38
     examples
    1.27
    Activations Density 0.040%

    No Known Activations