© 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. 13-GEMMASCOPE-2-RES-65K
    4. 1014
    Prev
    Next
    INDEX
    Explanations

    how can i help you today

    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_13_width_65k_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
    𝗽
    1.65
    eping
    1.50
    ্কর
    1.36
     minst
    1.34
    𝗹
    1.33
    gul
    1.29
    gaben
    1.28
    𝘁
    1.28
    epers
    1.26
    )||
    1.26
    POSITIVE LOGITS
     पेर
    1.81
    ⓪
    1.76
    ванович
    1.62
    生の
    1.62
     बनाई
    1.58
    мерикан
    1.58
    aad
    1.55
    рк
    1.53
    І
    1.52
    堅
    1.49
    Activations Density 0.077%

    No Known Activations