© 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. 102402
    Prev
    Next
    INDEX
    Explanations

    early age or stage

    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
    竇
    -0.82
     месяца
    -0.82
    Է
    -0.75
    ","","
    -0.72
    RRR
    -0.71
     последний
    -0.71
     segmentos
    -0.71
    ajemen
    -0.71
    പ്
    -0.70
    anteil
    -0.70
    POSITIVE LOGITS
     early
    4.00
     an
    3.47
    early
    3.23
     earliest
    3.03
    Early
    3.00
     earlier
    3.00
     Early
    2.81
     ран
    2.72
    EARLY
    2.67
     EARLY
    2.56
    Activations Density 0.081%

    No Known Activations