© 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. 7-GEMMASCOPE-2-RES-16K
    7. 446
    Prev
    Next
    INDEX
    Explanations

    't' following quotes

    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_7_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
    żą
    1.86
    দু
    1.60
    ž
    1.56
    ੍ਹ
    1.54
     zusätzlichen
    1.53
    middels
    1.52
    둘
    1.52
    ábban
    1.47
    ਜ
    1.46
    ếp
    1.46
    POSITIVE LOGITS
     concentrating
    2.13
     concentrates
    2.07
     Во
    2.02
    ом
    1.98
     concentrate
    1.98
    sframe
    1.92
    buster
    1.91
    sman
    1.87
    amers
    1.86
    ы
    1.85
    Activations Density 0.159%

    No Known Activations