© 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. 77332
    Prev
    Next
    INDEX
    Explanations

    a mistakea fighta stirringan extremelya rarea Barclaysa surprisinga heartbreakinga raucousa shutouta four-match

    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
    mings
    -0.96
    razine
    -0.91
    定食
    -0.84
    🌄
    -0.81
     espectáculos
    -0.80
    ogical
    -0.79
    swire
    -0.79
    izational
    -0.79
    ogh
    -0.78
    Ghz
    -0.78
    POSITIVE LOGITS
     hígado
    0.98
     forget
    0.91
    つづく
    0.88
     encouraging
    0.88
     unsere
    0.88
    不舒服
    0.87
     blessure
    0.86
     inspired
    0.85
    whis
    0.84
     confident
    0.83
    Activations Density 0.034%

    No Known Activations