© 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. 22-GEMMASCOPE-RES-131K
    7. 69108
    Prev
    Next
    INDEX
    Explanations

    names and aliases

    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
     ,‬
    -1.09
     redus
    -1.02
     entusias
    -0.98
     チェア
    -0.98
     construit
    -0.95
     たま
    -0.93
     ジップ
    -0.90
    formerly
    -0.90
     gän
    -0.89
    ១
    -0.89
    POSITIVE LOGITS
     Taking
    1.19
     using
    1.08
     burgeoning
    1.05
     pseud
    1.04
     Many
    1.03
     Putting
    1.02
     Those
    1.02
     dazzling
    1.01
     an
    0.99
     putting
    0.97
    Activations Density 0.069%

    No Known Activations