© 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. 2594
    Prev
    Next
    INDEX
    Explanations

    friendship

    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
    вающие
    1.96
    itated
    1.83
    ून्य
    1.80
    يح
    1.77
    晗
    1.72
    vaa
    1.71
    ᴀ
    1.70
    ваются
    1.70
     красо
    1.70
    𝘃
    1.67
    POSITIVE LOGITS
    ত্বের
    2.02
    谊
    1.93
    hold
    1.91
    liness
    1.88
    y
    1.79
    lichkeit
    1.78
    yb
    1.75
     circles
    1.75
    誼
    1.74
    朋
    1.72
    Activations Density 0.311%

    No Known Activations