© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4590
    Prev
    Next
    INDEX
    Explanations

    x² + 2x + 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >′
    0.78
    stuffs
    0.68
    Ϊ
    0.68
     извър
    0.66
    נם
    0.65
    贰
    0.64
     cực
    0.63
     inclination
    0.63
    শিয়ার
    0.63
    ीजन
    0.63
    POSITIVE LOGITS
    g
    0.82
    ali
    0.81
    kick
    0.76
    ли
    0.72
    z
    0.71
    ात
    0.70
    зова
    0.69
    ca
    0.68
    alt
    0.67
    alan
    0.67
    Activations Density 0.011%

    No Known Activations