© 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. 78054
    Prev
    Next
    INDEX
    Explanations

    Supreme Court of states

    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
    bec
    -0.78
     exquisite
    -0.76
    Getty
    -0.73
     Leute
    -0.72
     MutableLiveData
    -0.70
     caminhada
    -0.68
    товый
    -0.67
     温
    -0.66
     exquisitely
    -0.65
    Демографія
    -0.65
    POSITIVE LOGITS
     igni
    0.82
     RAG
    0.80
     Barba
    0.76
     veranda
    0.75
     Sanctuary
    0.75
    Suche
    0.75
    奂
    0.75
    rary
    0.75
     ceo
    0.72
    Oso
    0.70
    Activations Density 0.047%

    No Known Activations