© 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. 11884
    Prev
    Next
    INDEX
    Explanations

    voltage, angle, wavelength

    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
     lasts
    1.14
     hurts
    1.13
     Techniques
    1.12
    nextNode
    1.10
     methods
    1.09
    ｓ
    1.09
     Methods
    1.07
     date
    1.07
     пока
    1.06
     decreases
    1.06
    POSITIVE LOGITS
    avasena
    1.91
    zuc
    1.89
    oje
    1.88
    ený
    1.86
    此之外
    1.81
    appui
    1.78
    нная
    1.78
    ੀ
    1.78
    ன்
    1.76
    zecz
    1.73
    Activations Density 0.006%

    No Known Activations