© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1765
    Prev
    Next
    INDEX
    Explanations

    phone accessories and grips

    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
    erven
    1.32
    ăș
    1.26
    ^*(\
    1.22
    ärt
    1.21
    示例
    1.14
    áč
    1.13
    ád
    1.12
    éb
    1.11
    Elsewhere
    1.11
    *:
    1.09
    POSITIVE LOGITS
     inorder
    1.77
     which
    1.77
     equipments
    1.76
     inbuilt
    1.75
     everytime
    1.72
     whilst
    1.67
     loosing
    1.65
     firstly
    1.59
     upto
    1.58
     learnt
    1.55
    Activations Density 0.141%

    No Known Activations