© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4994
    Prev
    Next
    INDEX
    Explanations

    joke punchlines starting with because

    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_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
    ান
    1.79
    ل
    1.79
    需要
    1.65
    𝗅
    1.60
    لر
    1.57
    نہ
    1.55
    ಿಕ
    1.49
    堂
    1.48
    fek
    1.48
    トリ
    1.46
    POSITIVE LOGITS
    Soft
    2.01
     manners
    1.97
     dáng
    1.90
    statics
    1.84
    plers
    1.82
    Busy
    1.82
     Hard
    1.81
     AVAudio
    1.81
     בלי
    1.79
     Summar
    1.79
    Activations Density 0.241%

    No Known Activations