© 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. 77419
    Prev
    Next
    INDEX
    Explanations

    origins of names and words

    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
     improves
    -0.88
     売り
    -0.85
     письмо
    -0.85
    образие
    -0.83
     kool
    -0.81
    ִּי
    -0.81
    Merhaba
    -0.80
    🦮
    -0.80
     pngtree
    -0.80
     pagină
    -0.80
    POSITIVE LOGITS
     corrupted
    1.39
     derivatives
    1.34
     contraction
    1.30
     производ
    1.23
     formations
    1.17
     feminine
    1.16
     diminutive
    1.15
     compuesto
    1.13
     derived
    1.09
    corruption
    1.08
    Activations Density 0.059%

    No Known Activations