© 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. 99649
    Prev
    Next
    INDEX
    Explanations

    model modelmodel building kit

    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
    ニメ
    -0.87
    Villa
    -0.84
    NODES
    -0.81
    jfree
    -0.81
     trad
    -0.75
    зія
    -0.75
    Flux
    -0.74
    otti
    -0.74
     Pisa
    -0.71
     Physics
    -0.71
    POSITIVE LOGITS
     Modelling
    1.20
    Modelling
    1.19
     modelling
    1.16
    Modeling
    1.12
     modeling
    1.10
     Modeling
    1.09
     kit
    1.09
     build
    1.06
     modell
    1.04
     builds
    0.99
    Activations Density 0.013%

    No Known Activations