© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3676
    Prev
    Next
    INDEX
    Explanations

    People's Republic of China

    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
     TO
    2.79
     Raise
    2.73
     출
    2.64
    ة
    2.61
     Φ
    2.54
     φ
    2.51
     e
    2.50
     Μ
    2.46
    ّه
    2.45
     번째
    2.44
    POSITIVE LOGITS
    tub
    3.55
    t
    3.09
    dır
    2.98
    هایی
    2.98
    europa
    2.86
    Bern
    2.75
    يں
    2.71
    enfant
    2.71
    economia
    2.70
    آ
    2.69
    Activations Density 0.004%

    No Known Activations