© 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. 15725
    Prev
    Next
    INDEX
    Explanations

    stop actions or processes

    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
    椏
    2.25
    鴦
    2.07
     औसत
    2.00
    верса
    1.98
    ivas
    1.96
    issez
    1.96
     Praise
    1.95
    ോധ
    1.95
    း
    1.93
    ivalent
    1.90
    POSITIVE LOGITS
    𝒆
    2.65
    िओ
    2.31
     "*");
    2.28
    𝒉
    2.19
    𝒊
    2.15
    팅
    2.12
    𝒂
    2.09
    ی
    2.01
     හි
    1.99
    𝒏
    1.94
    Activations Density 0.090%

    No Known Activations