© 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. 3223
    Prev
    Next
    INDEX
    Explanations

    morality, values, ethics

    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
    propTypes
    3.04
    毫
    2.75
    Ꮖ
    2.66
    parentNode
    2.59
    𒁳
    2.54
     Fourier
    2.54
    subTest
    2.53
    Է
    2.50
    Ρ
    2.47
    nection
    2.43
    POSITIVE LOGITS
    rások
    3.00
     .....
    2.84
    ProductRunnable
    2.66
    anı
    2.57
    ামুটি
    2.55
    '،
    2.54
    anın
    2.52
    че
    2.52
     ....
    2.51
    yek
    2.50
    Activations Density 0.062%

    No Known Activations