© 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. 33257
    Prev
    Next
    INDEX
    Explanations

    ordinal rankings and draft rounds

    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
     перено
    -0.82
    ostructures
    -0.78
    最強
    -0.78
     Accepted
    -0.77
    DataSnapshot
    -0.77
    Firstly
    -0.70
     Winfield
    -0.69
    uckle
    -0.68
    phis
    -0.68
    дать
    -0.68
    POSITIVE LOGITS
     fourth
    1.64
     fifth
    1.63
     third
    1.54
     seventh
    1.53
     sixth
    1.48
    fourth
    1.26
    fifth
    1.14
    Fourth
    1.13
    Fifth
    1.13
     eighth
    1.10
    Activations Density 0.021%

    No Known Activations