© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7233
    Prev
    Next
    INDEX
    Explanations

    older cancer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
    ᒫ
    0.74
    vertexBuffer
    0.71
     désir
    0.69
    vær
    0.66
     cookbooks
    0.66
    żeń
    0.65
     desea
    0.65
     sostiene
    0.65
     pihak
    0.65
     locaux
    0.63
    POSITIVE LOGITS
     Best
    0.97
     best
    0.89
    <0xE2>
    0.85
    Best
    0.83
     Controllers
    0.81
     Flash
    0.78
     Excess
    0.78
     Cheat
    0.77
     Solution
    0.76
     Controller
    0.75
    Activations Density 0.000%

    No Known Activations