© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170293
    Prev
    Next
    INDEX
    Explanations

    high risk, failures, kill growth

    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
    ков
    0.47
     hòa
    0.46
     in
    0.45
     ná
    0.45
     enjoying
    0.45
     egli
    0.43
     Ś
    0.43
    Ô
    0.43
     آدمی
    0.43
     hành
    0.42
    POSITIVE LOGITS
    Singleton
    0.52
    rapes
    0.50
    ror
    0.47
    ptives
    0.47
     chatbots
    0.45
    ains
    0.45
    iciencia
    0.45
    /).
    0.44
    yp
    0.44
    ছনে
    0.44
    Activations Density 0.003%

    No Known Activations