© 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. 53018
    Prev
    Next
    INDEX
    Explanations

    identifying instructions and descriptions

    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
    🧩
    0.51
     подобных
    0.51
     globales
    0.50
     percentuale
    0.50
     baisse
    0.49
     ቀላል
    0.49
    ሮችን
    0.49
     ミニ
    0.49
     matrice
    0.49
     подобные
    0.49
    POSITIVE LOGITS
    Ch
    0.48
    时
    0.45
    王
    0.45
    H
    0.45
    ти
    0.44
    week
    0.43
    Eh
    0.43
    علی
    0.41
    粗
    0.41
    জি
    0.41
    Activations Density 0.004%

    No Known Activations