© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84672
    Prev
    Next
    INDEX
    Explanations

    spaces around commas and operators

    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_40_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
     Abstand
    0.41
     мг
    0.39
    ни
    0.38
     années
    0.38
     расстоянии
    0.38
    в
    0.38
     eu
    0.37
     distance
    0.37
     guerra
    0.37
    мо
    0.37
    POSITIVE LOGITS
    āv
    0.41
    branched
    0.40
    orchid
    0.39
    ಹೆ
    0.39
    จึง
    0.39
    博物館
    0.39
    colorbar
    0.39
    aloo
    0.38
    掫
    0.38
     adhipp
    0.38
    Activations Density 0.002%

    No Known Activations