© 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. 2045
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind

    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
    हेब
    2.94
    __(/*!
    2.62
     filos
    2.54
    niveau
    2.45
    跶
    2.42
    t
    2.41
    andır
    2.39
     Loretta
    2.32
    荑
    2.30
    tien
    2.26
    POSITIVE LOGITS
    şen
    2.74
     subalgebra
    2.74
    कुंठ
    2.61
     recog
    2.60
    ্ধ
    2.50
    िक
    2.41
    気が
    2.39
    蔽
    2.39
    itatis
    2.37
    டை
    2.35
    Activations Density 0.155%

    No Known Activations