Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2587
    Prev
    Next
    INDEX
    Explanations

    Key improvements and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    <0x0D>
    0.41
     acier
    0.41
     acciaio
    0.37
     গঠিত
    0.36
    ুতের
    0.36
     Zeus
    0.35
     Deluxe
    0.34
     Quân
    0.34
     métallique
    0.34
     forskellige
    0.34
    POSITIVE LOGITS
    :
    0.46
     ресу
    0.42
    원은
    0.42
    meldung
    0.41
    :“
    0.40
     замеча
    0.39
     informant
    0.39
    ✳
    0.38
     моя
    0.37
     首先
    0.37
    Activations Density 0.086%

    No Known Activations