© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4882
    Prev
    Next
    INDEX
    Explanations

    asking for needs and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    6
    1.01
    3
    1.01
    5
    0.87
    0
    0.86
    找不到
    0.85
    8
    0.82
    อิ
    0.80
    9
    0.79
    吉祥
    0.79
    ผ
    0.79
    POSITIVE LOGITS
     terutama
    2.14
     zejména
    2.14
     insbesondere
    2.03
     notably
    2.01
     soprattutto
    1.98
     особенно
    1.97
     khususnya
    1.96
     especially
    1.96
     particularly
    1.95
    尤其
    1.94
    Activations Density 0.210%

    No Known Activations