© 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. 89866
    Prev
    Next
    INDEX
    Explanations

    goes beyond

    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
     выглядит
    -0.85
    tawesome
    -0.84
    Forever
    -0.84
    עד
    -0.82
    мма
    -0.81
    ∀
    -0.81
    )};
    -0.81
    wiz
    -0.80
     fábricas
    -0.79
     $"{
    -0.79
    POSITIVE LOGITS
     extends
    3.19
     goes
    2.88
     extend
    2.72
    extend
    2.22
    extends
    2.11
     go
    2.02
     extending
    1.97
     Extend
    1.96
     isn
    1.91
    goes
    1.84
    Activations Density 0.068%

    No Known Activations