© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72451
    Prev
    Next
    INDEX
    Explanations

    its followed by description

    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
    -2.67
    ,”
    -2.23
    ”
    -2.08
     \
    -2.06
     Когда
    -2.02
     When
    -1.96
    ”.
    -1.95
     to
    -1.92
    L
    -1.92
    ↵
    -1.91
    POSITIVE LOGITS
    StoryboardSegue
    2.63
    鲼
    2.58
    躑
    2.41
    呓
    2.25
    
    2.16
     Saltar
    2.16
    ᠊
    2.13
    彐
    2.09
    
    2.09
    縯
    2.08
    Activations Density 0.023%

    No Known Activations