© 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. 2210
    Prev
    Next
    INDEX
    Explanations

    multilingual characters and diverse scripts

    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
    を通して
    1.06
     EVERYTHING
    0.97
     POSSIBLE
    0.95
     BOTH
    0.89
     possible
    0.88
     BECAUSE
    0.87
    %:
    0.87
     ANYTHING
    0.87
    点を
    0.87
     THROUGH
    0.87
    POSITIVE LOGITS
     huh
    1.45
     nhỉ
    1.25
     eh
    1.21
    นะ
    1.16
     그죠
    1.16
    ね
    1.16
    よね
    1.15
     그렇죠
    1.13
    嘛
    1.13
     aye
    1.12
    Activations Density 0.379%

    No Known Activations