© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5615
    Prev
    Next
    INDEX
    Explanations

    multilingual dictionary entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    hör
    0.93
    camb
    0.91
    },-\
    0.87
    teras
    0.85
    inqu
    0.81
    addy
    0.75
    orgement
    0.74
    ivables
    0.73
     başlam
    0.71
    hö
    0.70
    POSITIVE LOGITS
     ejerc
    1.74
    판
    1.64
    商务
    1.64
    勢
    1.61
     exerted
    1.60
    系
    1.58
    並
    1.58
    まん
    1.57
    当
    1.56
    连
    1.55
    Activations Density 0.027%

    No Known Activations