© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10495
    Prev
    Next
    INDEX
    Explanations

    you want or need

    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_22_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
    MemoryWarning
    1.04
     impl
    0.88
    达
    0.86
     aku
    0.80
     furt
    0.79
    प्ली
    0.78
    ]}/
    0.76
     miei
    0.75
    aj
    0.75
     kapt
    0.75
    POSITIVE LOGITS
     ALF
    0.91
    ARK
    0.86
    髙
    0.84
    Utf
    0.83
    眺
    0.81
    SiO
    0.81
     Witch
    0.80
    銘
    0.79
    анали
    0.79
     বক্ত
    0.79
    Activations Density 0.037%

    No Known Activations