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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 751
    Prev
    Next
    INDEX
    Explanations

    linguistic, established, Policy

    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_65k_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
    ප
    1.39
    Juven
    1.31
    素敵な
    1.29
    TouchableOpacity
    1.27
    जन्म
    1.26
     एजुकेशन
    1.25
    ĩnh
    1.23
     remaja
    1.23
    Males
    1.23
     Wilkes
    1.21
    POSITIVE LOGITS
     pon
    1.00
     to
    0.98
     reinforcing
    0.96
     +
    0.96
     making
    0.94
     high
    0.93
     bites
    0.92
     pointing
    0.91
     plus
    0.89
     PCR
    0.88
    Activations Density 0.000%

    No Known Activations