© 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. 14210
    Prev
    Next
    INDEX
    Explanations

    bring back home

    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
    generate
    1.94
    ت
    1.88
    totally
    1.77
    تو
    1.76
    ት
    1.72
    get
    1.71
    全然
    1.70
    息
    1.68
    本来
    1.68
    ्ता
    1.67
    POSITIVE LOGITS
     څه
    2.02
    倖
    2.02
    MemoryWarning
    1.91
     Rais
    1.90
    otted
    1.88
     바라
    1.85
     Dus
    1.82
    žite
    1.81
     contemplates
    1.81
    候
    1.81
    Activations Density 0.047%

    No Known Activations