© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9421
    Prev
    Next
    INDEX
    Explanations

    string manipulation and calculation

    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_22_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
    排序
    1.07
    蹙
    1.01
     orde
    0.99
     straightening
    0.98
     slaw
    0.95
     පිට
    0.93
     Gestión
    0.92
     käs
    0.91
     hojas
    0.90
     言
    0.90
    POSITIVE LOGITS
    Activ
    1.06
    Acad
    1.04
     सम्राट
    1.03
    Sec
    0.98
     Revolt
    0.98
    Untuk
    0.98
    Rq
    0.97
    Experiment
    0.96
    Transition
    0.96
    Both
    0.96
    Activations Density 0.000%

    No Known Activations