© 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. 6406
    Prev
    Next
    INDEX
    Explanations

    acrid, acropolis, terminal

    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
    Ẳ
    0.80
    enció
    0.74
    try
    0.71
    раз
    0.66
    cosh
    0.66
    aines
    0.65
    ]---
    0.64
    hasOwnProperty
    0.64
     изме
    0.62
     چرا
    0.61
    POSITIVE LOGITS
     secondi
    1.78
    verbs
    1.72
    知り
    1.71
    speak
    1.65
    imer
    1.64
    рій
    1.64
     mengenal
    1.61
     mism
    1.60
    拔
    1.60
    osaurs
    1.59
    Activations Density 0.107%

    No Known Activations