© 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. 107454
    Prev
    Next
    INDEX
    Explanations

    on the other hand

    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
     those
    -1.46
     a
    -1.38
     that
    -1.28
     this
    -1.25
     these
    -1.22
     their
    -1.15
    THE
    -1.14
     an
    -1.13
    他是
    -1.11
     what
    -1.06
    POSITIVE LOGITS
     the
    2.78
    reviewed
    1.05
     Karakter
    0.94
    Wenn
    0.92
    uParam
    0.92
     ตัว
    0.91
    addComponent
    0.91
    ˃
    0.91
     mamá
    0.90
    ˂
    0.89
    Activations Density 0.104%

    No Known Activations