© 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. 3688
    Prev
    Next
    INDEX
    Explanations

    Prevention Lifeline

    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
     hairdryer
    2.04
    မ့်
    1.89
     waterline
    1.89
    impin
    1.86
     forceps
    1.83
    光
    1.82
     δὲ
    1.81
    פּ
    1.80
     tray
    1.78
    中华人民共和国
    1.78
    POSITIVE LOGITS
    lari
    2.41
    elmi
    2.23
    kans
    2.23
    乎
    2.22
    lom
    2.21
    t
    2.18
    ي
    2.15
    lir
    2.07
    uencia
    2.07
     صدا
    2.06
    Activations Density 0.011%

    No Known Activations