© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 7727
    Prev
    Next
    INDEX
    Explanations

    generate explanations or content

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

    imperative, task-directing phrasing in user prompts (instructions that tell the model to do something)

    oai_token-act-pair · gpt-5Triggered 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
     সম্পর্ক
    0.27
     whenever
    0.26
     পর্যাপ্ত
    0.26
     faciliter
    0.25
     alınd
    0.25
    সাব
    0.25
     অস্ব
    0.25
    চাল
    0.25
     defaulting
    0.25
     Anytime
    0.25
    POSITIVE LOGITS
    adolu
    0.31
    ​—
    0.29
    様専用
    0.28
    ʼ
    0.28
     एगो
    0.27
    ère
    0.27
     anunció
    0.26
    enido
    0.26
    чора
    0.25
    lepší
    0.25
    Activations Density 0.532%

    No Known Activations