© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2959
    Prev
    Next
    INDEX
    Explanations

    house and hardware

    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
     useAppContext
    2.65
    калә
    2.61
    iziert
    2.55
    酞
    2.52
    zie
    2.49
    }}}-\
    2.44
    玑
    2.42
    HEIM
    2.39
    colorControl
    2.38
    WillAppear
    2.38
    POSITIVE LOGITS
    បន្ថ
    2.57
    eness
    2.32
    borders
    2.30
     Nationalism
    2.26
    em
    2.20
    Knife
    2.12
    primary
    2.10
    𝑛
    2.03
    合物
    2.01
    𝑒
    2.00
    Activations Density 0.187%

    No Known Activations