© 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. 65989
    Prev
    Next
    INDEX
    Explanations

    named entities followed by context

    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
    ⓛ
    -0.84
    光
    -0.77
    atea
    -0.76
    ໒
    -0.73
     pediatrician
    -0.72
    iligt
    -0.71
    Gods
    -0.71
     Może
    -0.71
    ApiException
    -0.70
     refiri
    -0.70
    POSITIVE LOGITS
    Javascript
    0.74
     hábit
    0.72
     forever
    0.69
     कोण
    0.69
    nants
    0.69
     feeling
    0.67
     Polski
    0.67
     Emmett
    0.66
     disappear
    0.65
    сами
    0.65
    Activations Density 0.018%

    No Known Activations