© 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. 33823
    Prev
    Next
    INDEX
    Explanations

    children and fun activities

    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
    niej
    -0.98
    嬰兒
    -0.93
     چوب
    -0.93
    ִּ
    -0.88
    ຣ
    -0.88
    TC
    -0.84
    blood
    -0.82
     πολι
    -0.82
    bier
    -0.81
     mihi
    -0.81
    POSITIVE LOGITS
     hours
    1.64
     encourage
    1.52
     kids
    1.52
     encourages
    1.46
     Encourage
    1.45
     stimulate
    1.41
    Encourage
    1.38
     estimular
    1.37
     children
    1.32
     Hours
    1.32
    Activations Density 0.037%

    No Known Activations