© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    storage

    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
    敲
    1.11
     선정
    1.06
     சீ
    1.03
     진행
    1.01
     przeprowad
    0.99
     드라마
    0.99
     방향
    0.96
    频率
    0.96
     번
    0.96
    切割
    0.95
    POSITIVE LOGITS
     storage
    2.28
     stockpile
    2.13
     Storage
    2.03
     penyimpanan
    2.02
     stockp
    2.02
     stockage
    2.01
    Storage
    1.97
    storage
    1.95
     armazen
    1.88
     almacenamiento
    1.86
    Activations Density 0.613%

    No Known Activations