© 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. 36372
    Prev
    Next
    INDEX
    Explanations

    search queries and results

    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
    󠁿
    0.39
     בין
    0.38
    leep
    0.37
    在其
    0.37
     खो
    0.36
    maketitle
    0.35
    柿
    0.35
     चाहें
    0.34
     ज़रूर
    0.34
    淦
    0.34
    POSITIVE LOGITS
    ิ่ม
    0.41
     ideas
    0.39
     residuals
    0.37
     rigorously
    0.37
     pozosta
    0.37
    빡
    0.36
    OHAMA
    0.36
    𝗽
    0.36
     screaming
    0.36
     Smy
    0.36
    Activations Density 0.024%

    No Known Activations