© 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. 14563
    Prev
    Next
    INDEX
    Explanations

    runway incursion

    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
    sman
    2.19
    s
    2.15
    ing
    2.12
    tional
    2.09
    ン
    2.07
    hipping
    1.92
    ellular
    1.91
    ske
    1.89
    sus
    1.82
    iye
    1.81
    POSITIVE LOGITS
    getConfiguration
    2.18
     meaning
    2.00
    体の
    1.98
     meanings
    1.97
    ᾧ
    1.91
    
    1.90
    кт
    1.89
    ګ
    1.86
    န်း
    1.84
     papeles
    1.82
    Activations Density 0.007%

    No Known Activations