© 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. 44491
    Prev
    Next
    INDEX
    Explanations

    talking about creatures, birth, or why to do something

    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
     buena
    0.37
    ink
    0.37
     Gases
    0.37
     dulu
    0.37
     beware
    0.36
    nyez
    0.36
    材
    0.35
     ink
    0.34
     jangan
    0.34
    ны
    0.34
    POSITIVE LOGITS
    显著
    0.45
     probabilistic
    0.45
     ನಾಗ
    0.45
     characterizes
    0.42
     अबू
    0.42
     মেয়ে
    0.40
     આનંદ
    0.40
     psychotic
    0.40
     elucidated
    0.40
    ရ
    0.40
    Activations Density 0.001%

    No Known Activations