© 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. 22-GEMMASCOPE-RES-131K
    7. 27830
    Prev
    Next
    INDEX
    Explanations

    use cases and features

    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_22/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
     that
    -1.25
    驚き
    -1.05
     instead
    -1.05
    quarelle
    -1.02
    isling
    -0.93
    聞いた
    -0.93
    倜
    -0.92
     преступ
    -0.92
    grees
    -0.91
    ceptable
    -0.91
    POSITIVE LOGITS
     you
    1.36
     olabilir
    1.12
    pas
    1.08
     also
    1.05
     quedado
    1.00
     your
    1.00
     mukaan
    1.00
    AMP
    0.96
    尤其
    0.96
     также
    0.95
    Activations Density 0.005%

    No Known Activations