© 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. 13930
    Prev
    Next
    INDEX
    Explanations

    German and English phrases about self

    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
     owed
    2.59
    াই
    2.53
    మి
    2.50
    ায়
    2.47
    CHEMY
    2.32
    ાદ
    2.30
    ㄚ
    2.28
    ⊰
    2.26
    recognized
    2.24
    #__
    2.23
    POSITIVE LOGITS
     proguardFiles
    2.71
    তান্ত্রিক
    2.69
    د
    2.66
    তিক্রম
    2.61
    todo
    2.59
    ził
    2.56
    意味
    2.55
    நே
    2.53
     безо
    2.52
    isho
    2.51
    Activations Density 0.008%

    No Known Activations