© 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. 14272
    Prev
    Next
    INDEX
    Explanations

    data augmentation

    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
    aksanakan
    2.02
     JsonSerializer
    1.97
    ąd
    1.93
    튠
    1.92
    ীভূত
    1.92
    otong
    1.91
     masak
    1.90
    俸
    1.89
    irti
    1.87
     বিদ্যালয়ের
    1.86
    POSITIVE LOGITS
    brack
    2.14
    Matthew
    2.06
    Ancient
    2.05
    LH
    2.03
    助于
    1.99
    Michael
    1.97
    Pre
    1.96
    ʣ
    1.96
    Thai
    1.94
    greek
    1.94
    Activations Density 0.000%

    No Known Activations