© 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. 45266
    Prev
    Next
    INDEX
    Explanations

    straight or direct usage

    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
     phonon
    -0.74
     augmente
    -0.74
     nomes
    -0.71
    rys
    -0.70
     убор
    -0.69
     Magnolia
    -0.69
    美子
    -0.68
     ha
    -0.67
     abzu
    -0.66
     Bassett
    -0.66
    POSITIVE LOGITS
     直
    1.23
    直
    1.17
     direct
    1.04
     직
    1.00
    irect
    0.91
     Zelle
    0.85
     thẳng
    0.83
     straight
    0.83
    Direct
    0.82
     preceding
    0.82
    Activations Density 0.011%

    No Known Activations