© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 9603
    Prev
    Next
    INDEX
    Explanations

    character names or identifiers followed by punctuation

    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_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
     hedon
    0.68
     x
    0.63
    s
    0.59
     s
    0.55
     unpredictable
    0.55
     always
    0.54
     f
    0.54
     love
    0.52
     S
    0.52
     competitive
    0.51
    POSITIVE LOGITS
     pergunt
    0.80
     whereupon
    0.79
    询问
    0.77
     pergunta
    0.75
     спраши
    0.74
     설명을
    0.74
    質問
    0.70
     preguntó
    0.66
     chiedere
    0.63
     поговори
    0.63
    Activations Density 0.006%

    No Known Activations