© 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. 11865
    Prev
    Next
    INDEX
    Explanations

    loading configuration or technology

    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
     then
    -1.31
     if
    -1.22
     in
    -1.19
     on
    -1.18
     with
    -1.17
     while
    -1.16
     despite
    -1.13
     had
    -1.06
     or
    -1.05
     becomes
    -1.05
    POSITIVE LOGITS
    "@
    1.23
    mostly
    1.13
    ⊥
    1.09
     คา
    1.09
    roughly
    1.09
    dding
    1.09
    nearly
    1.08
    potentially
    1.05
    athed
    1.05
    primarily
    1.05
    Activations Density 0.000%

    No Known Activations