© 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-65K
    7. 27470
    Prev
    Next
    INDEX
    Explanations

    positive or proactive 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_65k_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
    Obviously
    0.31
    蒨
    0.31
    etically
    0.29
    BALL
    0.29
    Caucasian
    0.29
    То
    0.29
    KG
    0.29
    ית
    0.28
    ELL
    0.28
    ூ
    0.28
    POSITIVE LOGITS
     whitew
    0.31
     Lore
    0.29
     esim
    0.28
     wallpaper
    0.27
     Greta
    0.27
     Rö
    0.26
     تقسيم
    0.26
     Murphy
    0.26
     viewModel
    0.26
     indoctr
    0.26
    Activations Density 0.137%

    No Known Activations