© 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. 100066
    Prev
    Next
    INDEX
    Explanations

    harmful actions

    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
    se
    0.59
    sw
    0.49
    Herz
    0.48
    S
    0.47
    ochen
    0.46
    T
    0.46
    Heart
    0.46
    Header
    0.44
    M
    0.44
    UI
    0.43
    POSITIVE LOGITS
     peces
    0.57
     caric
    0.52
     luce
    0.50
    ᱔
    0.50
    াচ্ছে
    0.49
     luces
    0.49
     usernames
    0.48
     minutos
    0.48
     tabela
    0.48
    ид
    0.48
    Activations Density 0.003%

    No Known Activations