© 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. 17757
    Prev
    Next
    INDEX
    Explanations

    but contrast

    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
    い
    0.55
    क
    0.52
    IA
    0.52
    ı
    0.51
    ం
    0.48
    いった
    0.46
    ü
    0.45
    AM
    0.44
    มอบ
    0.44
    IM
    0.44
    POSITIVE LOGITS
     digress
    0.64
    nél
    0.63
     sooo
    0.60
     soooo
    0.59
    ternut
    0.58
     dennoch
    0.56
    didn
    0.55
     není
    0.54
    termilk
    0.54
     irgendwie
    0.54
    Activations Density 0.005%

    No Known Activations