© 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. 84450
    Prev
    Next
    INDEX
    Explanations

    only one or a specific subset

    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
     there
    -1.61
     in
    -1.40
    และ
    -1.36
     because
    -1.29
     despite
    -1.27
     since
    -1.23
     for
    -1.23
     during
    -1.22
    钜
    -1.17
    ificantly
    -1.16
    POSITIVE LOGITS
     the
    1.80
    the
    1.21
     myös
    1.18
    also
    1.13
    our
    1.11
     wieder
    1.09
     your
    1.08
    ごとの
    1.02
    one
    1.02
     pintores
    1.01
    Activations Density 0.111%

    No Known Activations