© 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. 15629
    Prev
    Next
    INDEX
    Explanations

    code block closing tags

    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
     in
    -2.09
    Having
    -2.02
    While
    -1.80
    Although
    -1.80
    Since
    -1.80
    After
    -1.80
    Despite
    -1.77
    Because
    -1.75
     on
    -1.73
    There
    -1.70
    POSITIVE LOGITS
    跸
    1.57
    皷
    1.48
     crappy
    1.46
    
    1.41
     zweimal
    1.38
     abbildung
    1.35
     bedeutend
    1.34
     debacle
    1.32
    囡
    1.30
     horrible
    1.28
    Activations Density 0.005%

    No Known Activations