© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15690
    Prev
    Next
    INDEX
    Explanations

    documentation urls

    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_13_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
    llvm
    2.09
    apanicolaou
    2.03
    abre
    2.01
    𝘪
    1.95
    ണ്ഡി
    1.95
    럿
    1.94
    osito
    1.90
    PV
    1.86
    𝘮
    1.86
    𝗮
    1.85
    POSITIVE LOGITS
    ऩे
    2.48
    ]---
    2.11
    品
    2.09
    ]<
    2.06
    દર્
    2.05
    ध्यात्म
    2.04
    нув
    2.03
    stuffs
    2.02
    धुनिक
    2.01
    り
    1.98
    Activations Density 0.320%

    No Known Activations