© 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. 36163
    Prev
    Next
    INDEX
    Explanations

    even including evolved Nazis vibe relatively about

    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
    渗
    0.47
     الاشكال
    0.47
     বৈশিষ্ট্য
    0.45
    탯
    0.45
     možnost
    0.44
    eslintrc
    0.44
    lipstick
    0.44
    chette
    0.43
    רות
    0.43
    笏
    0.43
    POSITIVE LOGITS
    ido
    0.53
    et
    0.50
    사
    0.47
    在
    0.46
    n
    0.45
    ad
    0.42
     Perfecto
    0.42
    inga
    0.41
     Pass
    0.41
    umine
    0.40
    Activations Density 0.004%

    No Known Activations