© 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. 66601
    Prev
    Next
    INDEX
    Explanations

    true followed by );

    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
     of
    -1.76
     '
    -1.61
     "
    -1.48
     who
    -1.44
     we
    -1.39
     (
    -1.38
     to
    -1.38
     is
    -1.30
    </em>
    -1.26
      
    -1.20
    POSITIVE LOGITS
    6
    1.82
    焢
    1.70
     yapa
    1.47
    5
    1.46
    4
    1.45
    Даже
    1.45
    ጓ
    1.45
     pomegranate
    1.45
    8
    1.45
     Pingback
    1.42
    Activations Density 0.002%

    No Known Activations