© 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. 64887
    Prev
    Next
    INDEX
    Explanations

    parenting differentiated

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

    solving problems or making decisions

    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
    ר
    0.50
    贓
    0.49
     maioria
    0.48
     artículo
    0.47
    و
    0.47
    زاب
    0.46
    ן
    0.46
    avy
    0.46
     mandat
    0.46
    ري
    0.45
    POSITIVE LOGITS
     ойно
    0.51
    抚
    0.51
     отличаются
    0.50
     பண்ப
    0.50
    ücksicht
    0.45
     بیچ
    0.44
     جانتے
    0.44
     parenting
    0.43
     کیفیت
    0.43
    ifferentiated
    0.42
    Activations Density 0.000%

    No Known Activations