© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118514
    Prev
    Next
    INDEX
    Explanations

    direct connection or influence

    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
    ឵
    -1.18
    鵙
    -1.04
     dè
    -1.03
    ᕮ
    -1.02
     comprend
    -1.01
     دقیق
    -0.99
     विवरण
    -0.99
     anjo
    -0.99
     documenta
    -0.98
     deven
    -0.97
    POSITIVE LOGITS
     directly
    1.77
     direct
    1.52
     or
    1.48
     directamente
    1.34
     直接
    1.24
     Directly
    1.21
    Direct
    1.14
     Direct
    1.13
     enfrenta
    1.13
    direct
    1.12
    Activations Density 0.025%

    No Known Activations