© 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. 11805
    Prev
    Next
    INDEX
    Explanations

    groups acting or responsible

    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
     korun
    -0.91
    مؤ
    -0.85
    Dividend
    -0.81
    şit
    -0.77
    FERENCE
    -0.76
     cadáver
    -0.74
    raje
    -0.74
    ꪖ
    -0.73
    Obra
    -0.73
    ihnachts
    -0.73
    POSITIVE LOGITS
     who
    2.83
     participating
    2.28
     conducting
    2.19
     responsible
    2.13
     involved
    2.11
     overseeing
    2.11
     performing
    2.03
     administering
    1.98
     attending
    1.93
     supervising
    1.89
    Activations Density 0.273%

    No Known Activations