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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5884
    Prev
    Next
    INDEX
    Explanations

    baby and infant age stages

    np_acts-logits-general · gemini-2.5-flash-lite

    young humans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     публі
    0.60
     акча
    0.54
     लोकतांत्रिक
    0.54
     публи
    0.52
     इश्क
    0.51
    🛳
    0.49
     демокра
    0.48
    ቓ
    0.48
     санк
    0.48
    妓
    0.48
    POSITIVE LOGITS
     infants
    1.60
     infant
    1.59
     babies
    1.52
     newborns
    1.44
     Infants
    1.43
    婴儿
    1.42
     Infant
    1.41
     bebés
    1.41
     baby
    1.41
     newborn
    1.39
    Activations Density 0.349%

    No Known Activations