© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99790
    Prev
    Next
    INDEX
    Explanations

    question, tax, or specific days

    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_34/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
     passi
    -0.81
     approximated
    -0.79
     expl
    -0.79
     estimations
    -0.79
    Estimation
    -0.77
    CORRE
    -0.75
    colla
    -0.74
     detec
    -0.74
    を発
    -0.74
     faces
    -0.74
    POSITIVE LOGITS
     chi
    1.19
     goodness
    1.18
    χ
    1.16
    chis
    1.09
     quality
    1.09
     χ
    1.09
    merit
    1.06
     residuals
    1.05
    
    1.03
    chi
    1.02
    Activations Density 0.017%

    No Known Activations