© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110610
    Prev
    Next
    INDEX
    Explanations

    ages of children

    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
     बच्च
    -0.94
     or
    -0.91
    <b>
    -0.91
     Childhood
    -0.87
    <i>
    -0.83
     surrounding
    -0.81
     hundreds
    -0.81
     corresponden
    -0.81
     parecen
    -0.81
    <strong>
    -0.80
    POSITIVE LOGITS
     twins
    1.18
     aproape
    1.07
     teenager
    1.05
     почти
    0.99
     eldest
    0.99
     autistic
    0.97
     filha
    0.94
     soon
    0.94
     snart
    0.94
    来年
    0.91
    Activations Density 0.023%

    No Known Activations