© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2515
    Prev
    Next
    INDEX
    Explanations

    don't offer you

    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
    antin
    2.45
    andy
    2.41
     br
    2.22
    anten
    2.21
    sdale
    2.16
    𝙍
    2.16
    
    2.14
    unc
    2.12
    க்கொள்ள
    2.10
    witch
    2.09
    POSITIVE LOGITS
    \{{}\
    3.03
    खाव
    2.87
     appContext
    2.85
    当量
    2.78
    di
    2.78
    此之外
    2.74
     useAppContext
    2.71
    लिसिस
    2.68
    𝒍
    2.67
    加
    2.61
    Activations Density 0.090%

    No Known Activations