© 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. 14504
    Prev
    Next
    INDEX
    Explanations

    old AI

    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
    ்ட
    1.95
    𝐜
    1.90
    𝐡
    1.78
    uirre
    1.74
    とする
    1.72
    锲
    1.70
    uil
    1.68
    Wearing
    1.66
    挿
    1.66
    पिंग
    1.65
    POSITIVE LOGITS
     caballo
    1.99
     nó
    1.89
    ಲು
    1.89
     '\
    1.85
    此
    1.83
     faucibus
    1.83
    }$$
    1.80
    icado
    1.78
     bicicleta
    1.78
     nodo
    1.77
    Activations Density 0.035%

    No Known Activations