© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62797
    Prev
    Next
    INDEX
    Explanations

    spoil, paradox of choice

    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_41_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
     Saad
    0.38
    urov
    0.36
     કર
    0.35
    ="/">
    0.35
    сама
    0.35
    ͡
    0.35
     sapon
    0.34
     сам
    0.34
     jos
    0.34
    ₤
    0.34
    POSITIVE LOGITS
     spoiled
    1.82
     spoilt
    1.79
     spoil
    1.38
     spoiling
    1.34
    spo
    1.32
     Spo
    1.31
     spoils
    1.29
     spo
    1.20
    Spo
    1.11
     spoiler
    0.96
    Activations Density 0.003%

    No Known Activations