© 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. 15017
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens related to explicit sexual or bodily-content (nudity/genitalia) and other highly sensitive sexual/exploitative contexts.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     često
    0.48
     často
    0.47
     अक्सर
    0.46
     manchmal
    0.42
     glLight
    0.42
     często
    0.42
    랫폼
    0.42
    定义
    0.41
     signes
    0.40
     vedno
    0.40
    POSITIVE LOGITS
    怎么办
    0.55
     Luckily
    0.54
    しまった
    0.51
    しかも
    0.48
     உடனடியாக
    0.47
     Thankfully
    0.46
     predicament
    0.46
     awful
    0.46
     Ahora
    0.45
     sofort
    0.45
    Activations Density 0.121%

    No Known Activations