© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49172
    Prev
    Next
    INDEX
    Explanations

    bolded text and code

    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
    ukunft
    0.45
     कटोच
    0.41
     ограни
    0.40
     नीतियों
    0.39
    anca
    0.39
    冠
    0.39
    ings
    0.39
    िक
    0.39
    ices
    0.39
    ും
    0.38
    POSITIVE LOGITS
     Astronomy
    0.48
     ko
    0.47
     étape
    0.46
    lié
    0.46
    䞍
    0.46
     الا
    0.45
     malzem
    0.45
    เซ
    0.45
     bazı
    0.45
     Полу
    0.45
    Activations Density 0.008%

    No Known Activations