© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10522
    Prev
    Next
    INDEX
    Explanations

    cynical outlook or tone

    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
    𝗲
    3.17
    𝗶
    3.15
    𝘀
    3.14
    𝗿
    2.99
    𝗻
    2.98
    𝗼
    2.89
    است
    2.81
    ee
    2.78
    tedir
    2.76
     se
    2.75
    POSITIVE LOGITS
    ozyg
    3.33
    𝑔
    2.93
    咙
    2.90
    嚨
    2.84
    ులు
    2.83
    া
    2.82
    tering
    2.78
    ድረግ
    2.77
    на
    2.76
    teau
    2.75
    Activations Density 0.006%

    No Known Activations