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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 947
    Prev
    Next
    INDEX
    Explanations

    Allied Intelligence, Teenage Frontier, Guerra Mundial

    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
    Slot
    1.98
     निवास
    1.79
    elles
    1.77
    ণা
    1.76
    ண்க
    1.74
    icono
    1.73
    અ
    1.72
     Kurz
    1.68
    MAF
    1.67
    Noah
    1.67
    POSITIVE LOGITS
    𝑑
    2.01
    𝑙
    1.95
    𝑒
    1.94
     здо
    1.93
    רת
    1.93
     resistances
    1.89
    を切
    1.87
     AsyncTask
    1.86
    дика
    1.84
     resistance
    1.82
    Activations Density 0.220%

    No Known Activations