© 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. 13563
    Prev
    Next
    INDEX
    Explanations

    airline websites

    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
    स
    0.56
     load
    0.52
    ल
    0.52
     මෙම
    0.50
    ل
    0.49
    ،
    0.49
    ，
    0.48
     four
    0.48
     LOAD
    0.47
     Evalu
    0.47
    POSITIVE LOGITS
    ünsche
    0.49
    okban
    0.49
    ográf
    0.45
    watching
    0.45
    jac
    0.42
    ufthansa
    0.41
    új
    0.40
    几
    0.40
    lyPlugin
    0.40
    ích
    0.40
    Activations Density 0.003%

    No Known Activations