© 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. 98223
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    valis
    -0.81
    acruz
    -0.77
    fto
    -0.77
    awe
    -0.77
    heck
    -0.75
    owing
    -0.74
    creating
    -0.74
    created
    -0.73
    طي
    -0.73
     우리
    -0.72
    POSITIVE LOGITS
    AddNew
    0.77
    자인
    0.76
     zahlreiche
    0.75
     supremely
    0.74
     cuda
    0.73
    Linkedin
    0.73
    tualmente
    0.73
    nads
    0.73
     there
    0.72
    خواندن
    0.72
    Activations Density 0.033%

    No Known Activations