© 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-262K
    7. 10646
    Prev
    Next
    INDEX
    Explanations

    food and restaurant reservations

    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_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
    िशियल
    0.49
     Flights
    0.45
     꿈
    0.45
     له‌
    0.45
     Pogis
    0.44
     길
    0.44
    𝟖
    0.44
     Elite
    0.43
     Harness
    0.43
    꿈
    0.43
    POSITIVE LOGITS
    <0x80>
    0.52
    لو
    0.47
    лосо
    0.47
     handels
    0.46
    觀眾
    0.45
     mai
    0.44
     handheld
    0.44
    امد
    0.44
     informes
    0.44
     codice
    0.43
    Activations Density 0.001%

    No Known Activations