© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8839
    Prev
    Next
    INDEX
    Explanations

    accuracy and rigor

    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_13_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
    ,
    1.10
     fleeting
    1.01
     deepest
    0.96
     mysterious
    0.95
     tears
    0.94
     depths
    0.91
     tempt
    0.90
     habits
    0.90
     mythical
    0.89
     instinctive
    0.89
    POSITIVE LOGITS
    呮
    1.47
    譞
    1.39
    আরো
    1.36
    洮
    1.36
     vyz
    1.36
    很多的
    1.35
     zdravot
    1.33
     egyes
    1.31
     의료
    1.28
    ificacion
    1.28
    Activations Density 0.000%

    No Known Activations