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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 6012
    Prev
    Next
    INDEX
    Explanations

    condition

    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_all/layer_41_width_262k_l0_big
    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
    лями
    0.51
    ShaderType
    0.44
    យៈ
    0.42
    絠
    0.42
     চরিত
    0.41
    IFICATION
    0.41
    ื้อง
    0.41
    上位
    0.40
    粋
    0.40
     sweeter
    0.40
    POSITIVE LOGITS
     condition
    1.99
     Condition
    1.80
     состояние
    1.76
    Condition
    1.70
    condition
    1.66
     상태
    1.64
     состояния
    1.59
     Zustand
    1.59
     condição
    1.52
     condizione
    1.48
    Activations Density 0.003%

    No Known Activations