© 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. 128293
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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
     because
    -2.19
    :[],
    -1.63
     some
    -1.63
    ."
    -1.61
     they
    -1.52
     protože
    -1.49
     mengucap
    -1.48
     it
    -1.46
    :{},
    -1.45
     any
    -1.44
    POSITIVE LOGITS
    reggio
    1.52
     —
    1.47
     لت
    1.44
    讓你
    1.41
     are
    1.36
     μαζί
    1.34
    Your
    1.33
    lichung
    1.30
     onderdelen
    1.29
    ouflage
    1.28
    Activations Density 0.179%

    No Known Activations