© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58517
    Prev
    Next
    INDEX
    Explanations

    common phrases and titles

    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
    áce
    -0.88
     fucking
    -0.84
     Luckily
    -0.83
     sejauh
    -0.80
    Fuck
    -0.80
     getClient
    -0.80
     coinvol
    -0.79
    مكن
    -0.79
     usize
    -0.77
     prü
    -0.77
    POSITIVE LOGITS
     решений
    1.00
     BUILD
    0.81
     TBI
    0.80
    闭
    0.80
     Licenses
    0.79
    Solr
    0.78
     желание
    0.78
     MCF
    0.77
     Melee
    0.77
     minOccurs
    0.77
    Activations Density 0.000%

    No Known Activations