© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    buying, cooking, switch

    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
    utm
    1.89
    取
    1.69
    mlich
    1.67
    endale
    1.55
    keyframes
    1.53
    olus
    1.50
    —
    1.49
    —.
    1.46
     coalgebras
    1.46
    collar
    1.44
    POSITIVE LOGITS
     compleja
    2.30
     novoProduto
    2.28
    благо
    2.24
     kompleks
    2.21
     ponú
    2.18
     mult
    2.17
     ông
    2.13
     multifaceted
    2.11
    ากหลาย
    2.09
     tarefa
    2.09
    Activations Density 0.252%

    No Known Activations