© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98980
    Prev
    Next
    INDEX
    Explanations

    discusses or covers content

    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
     during
    -1.27
     before
    -1.16
     in
    -1.13
     final
    -1.11
     at
    -1.11
     time
    -1.09
     several
    -1.09
    した場合
    -1.09
     when
    -1.09
     five
    -1.06
    POSITIVE LOGITS
     anything
    1.23
     everything
    1.23
    anything
    1.22
    everything
    1.20
    mostly
    1.20
    sometimes
    1.19
     discusses
    1.17
    primarily
    1.16
    covering
    1.16
    discus
    1.13
    Activations Density 0.231%

    No Known Activations