© 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-262K
    7. 76986
    Prev
    Next
    INDEX
    Explanations

    bond or tool

    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_262k_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
    iamo
    0.43
    ę
    0.40
     isang
    0.40
     ilegal
    0.40
    Ox
    0.39
     hebben
    0.39
    èm
    0.39
     moeten
    0.39
    行驶
    0.39
     নিতান্ত
    0.38
    POSITIVE LOGITS
    塞
    0.46
    fü
    0.44
    莢
    0.44
    IGATION
    0.43
     zari
    0.42
     साप
    0.41
    插入
    0.41
     gatos
    0.41
     Plug
    0.41
     apice
    0.40
    Activations Density 0.013%

    No Known Activations