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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2007
    Prev
    Next
    INDEX
    Explanations

    thinking of memories

    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_17_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
     Echt
    0.92
    ประกาศ
    0.90
    原則
    0.86
     Finley
    0.83
    őbb
    0.80
    原则
    0.80
    웹
    0.80
     વૈ
    0.79
     Palt
    0.79
     unters
    0.79
    POSITIVE LOGITS
     memory
    4.34
     Memory
    4.04
     memories
    4.00
    memory
    3.91
    Memory
    3.82
    記憶
    3.70
     recollection
    3.67
     memoria
    3.57
     Memories
    3.56
     기억
    3.56
    Activations Density 0.890%

    No Known Activations