© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    following punctuation or conjunctions

    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
     ăn
    1.56
    '>
    1.50
     escrita
    1.49
    ஞ
    1.38
    পত্রের
    1.36
     bă
    1.34
     publicada
    1.34
     cum
    1.34
     manifest
    1.34
     ganzen
    1.31
    POSITIVE LOGITS
    ophenyl
    1.86
    borderRadius
    1.79
    emort
    1.78
     смер
    1.75
    笘
    1.75
    Დ
    1.74
     якому
    1.72
     preclinical
    1.71
    рея
    1.67
    拿下
    1.67
    Activations Density 0.000%

    No Known Activations