© 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. 48886
    Prev
    Next
    INDEX
    Explanations

    specifying context or conditions

    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
     кожного
    0.52
     сани
    0.49
    蘚
    0.48
     있지만
    0.46
     ܗܘ
    0.44
     саны
    0.44
     molybdenum
    0.44
    轍
    0.44
     ವೈ
    0.44
     регули
    0.43
    POSITIVE LOGITS
     Season
    0.59
     Context
    0.51
     context
    0.49
     Journey
    0.49
     Faces
    0.47
     audience
    0.47
     Agenda
    0.46
    观众
    0.46
     Pages
    0.46
     Meat
    0.46
    Activations Density 0.011%

    No Known Activations