© 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. 73233
    Prev
    Next
    INDEX
    Explanations

    kid, child, children

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

    kid or child

    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
    加え
    0.58
    𝗶
    0.54
    étricas
    0.52
    리에
    0.52
    varepsilon
    0.52
    ለጠ
    0.51
    م
    0.51
    만
    0.50
    頪
    0.50
    ரிய
    0.50
    POSITIVE LOGITS
     dziecka
    0.49
     can
    0.48
     çocuğ
    0.48
     child
    0.48
     yang
    0.47
     koko
    0.46
     sentient
    0.45
    spirator
    0.44
     criança
    0.44
     dítě
    0.44
    Activations Density 0.011%

    No Known Activations