© 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. 125303
    Prev
    Next
    INDEX
    Explanations

    technical systems and abstract concepts

    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
     waffles
    0.45
    我还
    0.44
    𝙜
    0.44
     jednotliv
    0.44
     Wanda
    0.44
    愪
    0.43
    偶
    0.42
     Donuts
    0.42
     〢
    0.41
     obstructions
    0.41
    POSITIVE LOGITS
    রাষ্ট্রে
    0.46
    wing
    0.44
     سین
    0.44
    arzt
    0.44
    라인
    0.43
    ског
    0.42
    ὥ
    0.42
    apy
    0.41
    맇
    0.41
    让他们
    0.40
    Activations Density 0.006%

    No Known Activations