© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103878
    Prev
    Next
    INDEX
    Explanations

    individuals and their involvement

    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
    omal
    -1.08
     becomes
    -0.98
    ency
    -0.98
    榻
    -0.95
    تهى
    -0.92
     bothers
    -0.91
     pertumbuhan
    -0.90
    emang
    -0.90
     mastery
    -0.88
    jarse
    -0.88
    POSITIVE LOGITS
     thinking
    1.63
     interested
    1.34
     involved
    1.13
    dreaming
    1.09
     excited
    1.08
     talking
    1.06
     convinced
    1.05
     заинтере
    1.00
     wondering
    0.99
     hooked
    0.99
    Activations Density 0.015%

    No Known Activations