© 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. 12529
    Prev
    Next
    INDEX
    Explanations

    rain, rainfall, and rainy weather

    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
    S
    2.36
    Interior
    2.30
    T
    2.27
    𝕣
    2.21
    Dik
    2.16
     bur
    2.09
    Din
    2.07
    пление
    2.06
    пления
    2.06
     interior
    2.06
    POSITIVE LOGITS
    ो
    3.00
     वर्षीय
    2.97
     वीं
    2.93
    ró
    2.73
    ोरा
    2.69
    年モデル
    2.66
    ópez
    2.64
    VISED
    2.59
    maket
    2.51
     सक्छ
    2.48
    Activations Density 0.015%

    No Known Activations