© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65670
    Prev
    Next
    INDEX
    Explanations

    skills and knowledge absence

    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
     martes
    -1.10
    ığımız
    -1.05
    lahoma
    -1.04
     पढ़ें
    -1.03
     iload
    -0.98
    ći
    -0.97
    гора
    -0.95
     tấn
    -0.95
    thérapie
    -0.94
     kors
    -0.94
    POSITIVE LOGITS
     skills
    1.51
     skilled
    1.32
     how
    1.27
     expertise
    1.24
     technical
    1.13
     skill
    1.09
     spesielt
    1.06
     навы
    1.02
     capabilities
    1.02
     know
    1.00
    Activations Density 0.045%

    No Known Activations