© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8194
    Prev
    Next
    INDEX
    Explanations

    un- prefixes creating negative concepts

    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_22_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
    👉
    0.94
     påver
    0.90
     👇
    0.89
     datap
    0.86
     breaths
    0.85
     கமல்
    0.85
     reimag
    0.85
     dunkel
    0.83
     kne
    0.82
    👇
    0.81
    POSITIVE LOGITS
    ells
    0.82
    ell
    0.79
    n
    0.74
    nica
    0.73
    ¦
    0.68
    œ
    0.66
    heid
    0.64
    ாள்
    0.64
    ella
    0.64
    שרה
    0.63
    Activations Density 0.051%

    No Known Activations