© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33584
    Prev
    Next
    INDEX
    Explanations

    Ramadan fasting from dawn to sunset

    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
    Compose
    0.37
    Increased
    0.37
    㖮
    0.37
    코
    0.36
    Doom
    0.36
    juna
    0.36
     هنگ
    0.36
    㢳
    0.35
    ја
    0.35
    解放
    0.35
    POSITIVE LOGITS
     Daytime
    0.41
     ಹೊಂದ
    0.41
    neros
    0.40
     daytime
    0.39
     Penalty
    0.39
     Fotograf
    0.38
     panther
    0.37
     Smok
    0.37
     nighttime
    0.37
     photographer
    0.37
    Activations Density 0.011%

    No Known Activations