© 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. 13155
    Prev
    Next
    INDEX
    Explanations

    deliberately followed by adjective

    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
    ভিয়েতনাম
    2.04
    ډ
    2.00
    といった
    1.99
     gramos
    1.97
     अभिकारक
    1.92
     Unfortunately
    1.90
    ódulo
    1.88
     Interestingly
    1.88
     tesam
    1.87
     convirtió
    1.87
    POSITIVE LOGITS
    abbr
    1.48
    WI
    1.39
    OWER
    1.36
    no
    1.34
    晓
    1.28
    ESI
    1.24
    li
    1.24
    ರ್ಭ
    1.22
    ns
    1.22
    ীয়
    1.22
    Activations Density 0.013%

    No Known Activations