© 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-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91038
    Prev
    Next
    INDEX
    Explanations

    Allah

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    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
     –
    0.68
    ;
    0.59
     -
    0.55
    ;</
    0.48
     Hungarian
    0.47
     Kenyan
    0.47
    ;.
    0.44
     Ecuadorian
    0.44
     Kerala
    0.44
    ;'
    0.43
    POSITIVE LOGITS
     Алла
    0.66
     {
    0.60
     الله
    0.57
    𝟭
    0.57
    {
    0.56
     والله
    0.56
     الم
    0.55
    ᱑
    0.54
     اللّه
    0.54
    ١
    0.53
    Activations Density 0.001%

    No Known Activations