© 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. 13-GEMMASCOPE-2-RES-16K
    7. 426
    Prev
    Next
    INDEX
    Explanations

    numbers and structure markers

    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_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
    യ
    1.51
     bárm
    1.48
     dearest
    1.48
    invocation
    1.43
    iciencia
    1.43
    Dev
    1.41
     επί
    1.40
    caso
    1.40
    cello
    1.40
    ęć
    1.39
    POSITIVE LOGITS
     roadblocks
    1.29
     OUTER
    1.24
     DISPLAYS
    1.23
    aned
    1.23
    辈
    1.20
     CONTINUE
    1.19
    ofacial
    1.18
    लीय
    1.18
    কারীদের
    1.18
     DISPLAY
    1.15
    Activations Density 0.000%

    No Known Activations