© 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. 209
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
    »
    1.36
    ын
    1.35
    CLAIM
    1.32
    ,»
    1.31
    birth
    1.29
    ὺς
    1.28
    .»
    1.27
    «
    1.26
    og
    1.25
    valt
    1.22
    POSITIVE LOGITS
    يج
    1.78
    تج
    1.66
    ος
    1.65
     แม
    1.62
    ీ
    1.59
    觟
    1.56
     ujarnya
    1.56
    köz
    1.56
    滀
    1.55
    
    1.54
    Activations Density 0.364%

    No Known Activations