© 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-16K
    7. 13736
    Prev
    Next
    INDEX
    Explanations

    British context and specific entities

    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_16k_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
     carers
    0.51
    law
    0.50
    🥰
    0.48
     Biden
    0.46
     Solicitor
    0.46
     საქართველოს
    0.46
     LGBTQ
    0.46
    legislation
    0.46
    🥺
    0.45
     solicitor
    0.45
    POSITIVE LOGITS
     αυ
    0.47
     బ్రిటిష్
    0.41
     Brit
    0.41
     Sereth
    0.41
     shrimp
    0.40
     ব্রিটিশ
    0.40
     কোষ
    0.40
    攻击
    0.39
     molti
    0.39
     Skype
    0.39
    Activations Density 0.038%

    No Known Activations