© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1518
    Prev
    Next
    INDEX
    Explanations

    I can offer guidance

    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_17_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
    ouard
    0.97
     Nutt
    0.92
    젝트
    0.92
     AudioManager
    0.90
     пробу
    0.88
    ㅆ
    0.87
     डील
    0.87
    빔
    0.85
    interference
    0.85
    til
    0.85
    POSITIVE LOGITS
    branes
    1.03
    opause
    0.95
    iotic
    0.88
    जब
    0.88
    iac
    0.84
    buat
    0.81
    brane
    0.80
    enek
    0.80
    ลา
    0.79
    ndez
    0.79
    Activations Density 0.354%

    No Known Activations