© 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. 56854
    Prev
    Next
    INDEX
    Explanations

    explaining incomplete contexts

    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
     v
    0.52
     nerd
    0.44
     aswell
    0.44
     oblik
    0.43
     akadem
    0.43
     tecnico
    0.42
    ॅक
    0.42
     ac
    0.42
     estudio
    0.41
     kol
    0.41
    POSITIVE LOGITS
     만든
    0.43
    이
    0.42
    ყოფ
    0.41
    스의
    0.40
    排除
    0.40
    ర్టు
    0.40
     했던
    0.40
    시킨
    0.39
    节日
    0.39
     THESE
    0.38
    Activations Density 0.014%

    No Known Activations