© 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. 1226
    Prev
    Next
    INDEX
    Explanations

    working on or with

    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
     Meets
    0.79
    ื่ม
    0.76
    ีน
    0.73
    ท
    0.73
     pozosta
    0.72
    กล่าว
    0.72
    s
    0.72
     पंकज
    0.71
    hape
    0.71
    ฮ
    0.71
    POSITIVE LOGITS
     tirelessly
    1.58
     onsite
    1.38
     workloads
    1.31
     cooperatives
    1.18
    <unused2175>
    1.18
     supervising
    1.17
     tireless
    1.17
     tasks
    1.17
    <unused2179>
    1.14
     renovating
    1.11
    Activations Density 0.600%

    No Known Activations