© 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. 64733
    Prev
    Next
    INDEX
    Explanations

    describing properties and states

    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
    ep
    -1.15
    ようだ
    -1.06
    bereich
    -0.98
     Хорошо
    -0.96
     comunidade
    -0.95
    ของ
    -0.94
    es
    -0.93
    of
    -0.92
    ↵↵
    -0.91
     gron
    -0.91
    POSITIVE LOGITS
     in
    1.27
    nesses
    1.27
     demais
    1.08
     Secara
    1.03
     overall
    1.02
     on
    1.02
    reebok
    1.02
     asiático
    0.99
     úl
    0.98
     tako
    0.98
    Activations Density 0.231%

    No Known Activations