© 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. 10-GEMMASCOPE-RES-131K
    7. 128299
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols

    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_10/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
    mancy
    -1.48
    掉的
    -1.45
    來
    -1.44
     procedere
    -1.40
    
    -1.39
     regionale
    -1.35
     commerci
    -1.34
     paſſ
    -1.30
     boe
    -1.30
     hef
    -1.30
    POSITIVE LOGITS
     what
    1.52
    3
    1.44
     after
    1.38
     during
    1.31
    wiad
    1.30
     it
    1.30
     before
    1.30
     Botschaft
    1.29
    紈
    1.27
     julk
    1.26
    Activations Density 0.001%

    No Known Activations