© 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. 4082
    Prev
    Next
    INDEX
    Explanations

    names

    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
     divination
    -0.81
     eels
    -0.79
     ']
    -0.77
     zouden
    -0.75
    肛
    -0.74
     colonna
    -0.73
    ustainable
    -0.73
     puissiez
    -0.73
     vět
    -0.72
     الأولى
    -0.72
    POSITIVE LOGITS
    uoš
    0.79
    ift
    0.76
    东京
    0.74
    期の
    0.73
    жда
    0.70
    ⣶
    0.70
    期的
    0.69
     suits
    0.69
    Descriere
    0.69
    连连
    0.68
    Activations Density 0.045%

    No Known Activations