© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52228
    Prev
    Next
    INDEX
    Explanations

    Islam and its practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ствии
    0.36
    бли
    0.36
    CONSOLE
    0.36
     பாவ
    0.35
    IsNullOrEmpty
    0.35
    恒
    0.35
     DIRECTION
    0.34
    த்து
    0.34
    VT
    0.34
    嶉
    0.34
    POSITIVE LOGITS
    elah
    0.40
     tattoos
    0.40
     ups
    0.39
     convertido
    0.39
     provoked
    0.39
     Tats
    0.38
     संतुलित
    0.38
     superfamily
    0.37
     verdienen
    0.37
    iko
    0.37
    Activations Density 0.009%

    No Known Activations