© 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. 418
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tim
    1.94
    őd
    1.83
    ʽ
    1.52
    nb
    1.52
    tw
    1.51
    sberg
    1.51
    ź
    1.50
    ikh
    1.48
     ਲ
    1.47
    ge
    1.46
    POSITIVE LOGITS
     auxilia
    1.32
     ","
    1.28
    ]-->
    1.26
    栈
    1.26
    ↵↵↵↵↵↵↵↵↵
    1.25
    ↵↵↵↵↵↵↵↵↵↵
    1.24
    Escolhido
    1.23
     principalColumn
    1.22
     действует
    1.22
    ફેદ
    1.22
    Activations Density 0.179%

    No Known Activations