© 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. 32479
    Prev
    Next
    INDEX
    Explanations

    child experiences and development

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

    child sexual abuse material

    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
    ↵↵
    0.71
     χρόνια
    0.70
     operações
    0.68
    મ
    0.66
    on
    0.65
     größte
    0.65
     ações
    0.64
     indiquée
    0.64
     cupboards
    0.64
     complète
    0.63
    POSITIVE LOGITS
    n
    1.00
    swear
    0.96
    ود
    0.85
    ని
    0.73
    🧒
    0.73
     الأطفال
    0.72
    r
    0.72
    们的
    0.71
    {
    0.70
    👶
    0.69
    Activations Density 0.090%

    No Known Activations