© 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. 98329
    Prev
    Next
    INDEX
    Explanations

    sixth or seventh round picks

    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
    vered
    -0.79
     pairwise
    -0.77
     partea
    -0.72
    ﹟
    -0.71
     burdensome
    -0.71
    Abuja
    -0.70
    chtest
    -0.70
     această
    -0.70
     costly
    -0.69
    THISDAY
    -0.69
    POSITIVE LOGITS
     und
    1.38
     UD
    1.29
     seventh
    1.20
     Seventh
    1.13
     sixth
    1.11
     Und
    1.08
    und
    0.99
    seventh
    0.95
    sixth
    0.94
     UND
    0.94
    Activations Density 0.033%

    No Known Activations