© 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. 31-GEMMASCOPE-2-RES-65K
    7. 48875
    Prev
    Next
    INDEX
    Explanations

    abstract god

    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
    udere
    0.45
    乖
    0.45
     cải
    0.44
    ご
    0.43
     его
    0.43
     транспорт
    0.42
    揀
    0.41
    榮
    0.41
     жена
    0.41
     транспорти
    0.40
    POSITIVE LOGITS
    ymmet
    0.44
     بتر
    0.43
     tav
    0.43
    vase
    0.42
    node
    0.42
     povo
    0.42
    NODE
    0.40
     lediglich
    0.40
     NODE
    0.40
    vano
    0.39
    Activations Density 0.006%

    No Known Activations