© 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. 36481
    Prev
    Next
    INDEX
    Explanations

    sequences and transitions

    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
     sqlSession
    -1.20
     because
    -1.16
     or
    -1.15
     régiment
    -1.10
     from
    -1.09
     ͡
    -1.02
     would
    -0.99
     _$
    -0.99
     before
    -0.96
    MÁS
    -0.96
    POSITIVE LOGITS
     intriguing
    1.09
     verkau
    1.08
     angek
    1.07
     astounding
    1.05
     Evaluación
    1.02
     acclaimed
    0.96
     gigantic
    0.96
     różnych
    0.95
     aufmerksam
    0.94
     intric
    0.94
    Activations Density 0.074%

    No Known Activations