© 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. 239
    Prev
    Next
    INDEX
    Explanations

    Infliximab, Bilawal, mathematical, protein, wordplay

    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
    갯
    1.91
     ki
    1.91
    蒜
    1.91
    쌈
    1.89
    콩
    1.89
     प्राइम
    1.88
     квартиру
    1.84
     baan
    1.83
     vitesses
    1.83
     Oriente
    1.81
    POSITIVE LOGITS
    t
    1.75
    ্বিক
    1.66
    ي
    1.66
    wght
    1.65
    ]))
    1.62
    uously
    1.60
    nell
    1.55
    teborg
    1.53
    ″]
    1.53
    städ
    1.52
    Activations Density 0.000%

    No Known Activations