© 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. 14093
    Prev
    Next
    INDEX
    Explanations

    fragments of memories and accounts

    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
     Sua
    2.13
     thế
    2.01
    τής
    1.96
     τὴν
    1.93
     τὸν
    1.93
     时
    1.87
     τὰ
    1.86
     tinggi
    1.83
     특
    1.82
     və
    1.80
    POSITIVE LOGITS
     leftover
    2.04
    剩
    2.00
     অবশিষ্ট
    1.98
     übrig
    1.96
     unsold
    1.87
    igm
    1.82
    assurance
    1.80
    Twig
    1.79
     बचे
    1.78
    orman
    1.75
    Activations Density 0.092%

    No Known Activations